{"chart-dashboard/analysis-agent":{"title":"Use Analysis Agent","category":"Chart Dashboard","slug":"chart-dashboard/analysis-agent","blurb":"Ask questions about your data and get AI-powered insights using the analysis agent.","order":2,"filename":"analysis-agent.md","uid":"chart-dashboard/analysis-agent","content":"\n# Use Analysis Agent\n\nThe analysis agent helps you explore your data by answering questions and providing insights about your charts and datasets.\n\n## Opening the analysis agent\n\n1. Click the **?** button in the bottom-right corner of your dashboard (or top-right if you're in dashboard mode).\n\n\n2. In the panel that opens, click **New conversation** and select **New analysis**.\n\n\n3. If you don't see the analysis option, make sure you have a project with data loaded and that the analysis agent feature is enabled for your account.\n\nOnce you've started a new analysis conversation, you can begin asking questions about your data.\n\n\n## Types of questions you can ask\n\n### Descriptions and summaries\n- \"What stands out in this chart?\"\n- \"Summarize the key differences between segments\"\n- \"What are the main patterns in the satisfaction data?\"\n\n### Comparisons\n- \"Compare satisfaction between Region and Product line\"\n- \"Which segments over-index on Positive responses?\"\n- \"How does NPS differ across customer segments?\"\n\n### Trends and patterns\n- \"Describe any notable trend over time for NPS\"\n- \"Highlight spikes or drops in this metric\"\n- \"What patterns do you see in the response rates?\"\n\n### Key drivers and relationships\n- \"What factors predict low satisfaction?\"\n- \"Find key drivers of intent to buy\"\n- \"Which columns are most related to customer retention?\"\n\n"},"chart-dashboard/dashboard-search":{"title":"Searching for columns","category":"Chart Dashboard","slug":"chart-dashboard/dashboard-search","blurb":"Quickly find columns using the dashboard search; matches include names and, if needed, category values.","order":1,"filename":"dashboard-search.md","uid":"chart-dashboard/dashboard-search","content":"# Searching for columns\n\nIn large datasets you may want to search on your chart dashboard for a particular column.\n\nThis can be done as follows:\n\nGo to your chart dashboard. For this dataset there are 113 columns visible. To quickly find a column you can use the search option on the left.\n\n\nType in the search input field to filter your chart dashboard. AddMaple will first find columns with a matching column name. In this example we've matched columns that have the word \"database\" in the column name. \n\n\nIf no column is found with a matching name, AddMaple will search within categories in a column. In this example columns have been found that have the word \"javascript\" as one of the categories.\n"},"chart-dashboard/editcolumns":{"title":"Editing column titles and types","category":"Chart Dashboard","slug":"chart-dashboard/editcolumns","blurb":"Rename columns and correct detected types directly from the Chart Dashboard.","order":2,"filename":"editcolumns.md","uid":"chart-dashboard/editcolumns","content":"# Chart Dashboard\n\n### Editing column titles and types\n\nYou can change the title of a column by clicking on it from the Chart Dashboard. An input box will appear where you can make your changes. Click the green tick button or press \"enter\" to save.\n\n\n\nAddMaple usually detects column types accurately, but occasionally we get it wrong. When this happens you can edit the column type by clicking on the type label or icon from the Chart Dashboard screen.\n\n\n"},"chart-dashboard/encryption":{"title":"How to encrypt and decrypt columns","category":"Chart Dashboard","slug":"chart-dashboard/encryption","blurb":"Encrypt sensitive columns locally, download the protected file, and decrypt columns when needed with your password.","order":3,"filename":"encryption.md","uid":"chart-dashboard/encryption","content":"# How to encrypt and decrypt columns\n\nAddMaple understands that sometimes you will have personally identifiable information (PII) or sensitive data in your dataset. Rather than expect you to remove sensitive columns and join it back later (which could lead to scrambling or other issues), we simply let you encrypt the sensitive columns while keeping the dataset intact.\n\nWhen you need the data from the sensitive columns, for example to email a specific customer, you can decrypt the data.\n\nThis is an example of a column containing PII that you may want to encrypt\n\n\nTo encrypt the column, go to the Chart Dashboard and then click on the More menu. Select \"Encrypt Columns\"\n\n\nA pop-up box will appear where you can select the column(s) that you would like to encrypt.\n\n\nEnter a password to encrypt your data. Please save this password somewhere safe as you will need this to decrypt your data later.\n\n\nAfter clicking \"Encrypt\", a new file will be downloaded to your computer. \n\n\nCreate a new project from the file that was downloaded in the previous step. You will see that any columns you selected to encrypt are shown on the Chart Dashboard as \"encrypted\".\n\n\nClick on the column to decrypt it. You will be shown a pop-up box and asked to enter the encryption password. If the password is correct, your data will be decrypted for your current session.\n"},"dashboard/add-items":{"title":"Add Items","category":"Dashboards","slug":"dashboard/add-items","blurb":"Add charts, text, images, sections, and KPI tiles to your dashboard pages.","order":3,"filename":"add-items.md","uid":"dashboard/add-items","content":"\n## Add items to a page\n\nUse the Actions menu or the floating Add button (when present).\n\n1. Open a dashboard page\n2. Click **Actions → Add to Dashboard** and choose an item type\n3. For Text, you can also use **Click to Place Text** and click anywhere on the grid\n\n\n\n---\n\n## Item types\n\n- **Text**: Rich text; inline edit with the edit icon\n- **Section**: Full-width heading block; uses project styles\n- **Call Out**: Highlight panel with border and background\n- **Image**: Paste URL or upload (uses `/api/images/upload`)\n- **Video**: YouTube, Vimeo, Loom, Wistia URLs (auto-embed)\n- **Charts**: Add via analysis save flows or from **My Collection**\n\n---\n\n## Insert charts\n\n- From analysis: use the save menu's **Add to Dashboard**\n- From **My Collection**: open the modal, select items, then **Add to Dashboard**\n\n\n\n\n"},"dashboard/arrange-items":{"title":"Arrange Items","category":"Dashboards","slug":"dashboard/arrange-items","blurb":"Move, align, and organize items with grid snapping and guides.","order":4,"filename":"arrange-items.md","uid":"dashboard/arrange-items","content":"\n## Move and resize\n\n- **Move**: Drag items anywhere on the fixed 12‑column grid (rowHeight 60)\n- **Resize**: Drag edges/corners; grid snaps with margins and padding applied\n\n\n\n---\n\n## Send to top/bottom\n\nUse the item toolbar to quickly move an item to the top (y=0) or to the bottom of the layout.\n\n---\n\n## Move to another page\n\nUse the item's \"Move to Page\" menu to send it to any other page in the dashboard.\n\n\n"},"dashboard/copy-paste":{"title":"Copy & Paste","category":"Dashboards","slug":"dashboard/copy-paste","blurb":"Copy items between pages and dashboards to reuse layouts and content.","order":5,"filename":"copy-paste.md","uid":"dashboard/copy-paste","content":"\n## Copying and pasting dashboard items\n\n1. Hover an item and click the **Copy** icon\n2. Switch page or open the target dashboard\n3. Press **⌘/Ctrl+V** to paste; items auto-position to available space\n\n\n\n\n---\n\n## Duplicate\n\n- Use Copy then Paste to duplicate on the same page; auto-placement prevents overlap\n\n---\n\n## What's copied\n\n- Full item content and style (including tailwind-based style settings)\n- Charts keep their settings; chart IDs are uniquified when coming from Collections\n\n\n"},"dashboard/create":{"title":"Create a Dashboard","category":"Dashboards","slug":"dashboard/create","blurb":"Create a new dashboard and set up your first page.","order":2,"filename":"create.md","uid":"dashboard/create","content":"\n## Create a new dashboard\n\nYou typically create dashboards from save flows or scratchpad selection. Learn more about [adding items to dashboards](../dashboard/add-items) and [arranging dashboard content](../dashboard/arrange-items).\n\n- From analysis/save: choose **Add to Dashboard** and select \"New dashboard\" (enter a name)\n- From My Collection: select items → **Add to Dashboard** → choose \"New dashboard\"\n- You can also duplicate an existing dashboard from its card or from inside the editor (Actions → Duplicate Dashboard)\n\n\n\n---\n\n## Add your first page\n\nNew dashboards start with one empty page.\n\n1. Click **Add page** (or use the Pages panel)\n2. Name your page (e.g. \"Overview\")\n3. Start adding items like charts, text, images, and KPIs\n\n\n\n---\n\n## Tips\n\n- Start with a single page and a simple layout. Add more pages as the story grows.\n- Use short, descriptive dashboard names so shared links are easy to recognize.\n- Add your logo from the header to brand your dashboard.\n\n\n"},"dashboard/edit-items":{"title":"Edit Items","category":"Dashboards","slug":"dashboard/edit-items","blurb":"Edit content, resize, duplicate, and delete dashboard items.","order":6,"filename":"edit-items.md","uid":"dashboard/edit-items","content":"\n## Select and edit\n\nClick any item to select it. Use the inline controls or the right-side panel (when available).\n\n\n\n---\n\n## Common edits\n\n- **Resize**: Drag item edges in the grid\n- **Delete**: Trash icon on the item toolbar\n- **Edit content**:\n - Text: click the edit icon to switch to the rich-text editor\n - Section/Call Out: edit text; styles come from the item style editor\n - Image: click \"Change Image\" to paste URL or upload\n - Video: click \"Change Video\" to paste a supported URL\n - Charts: open chart edit mode, then save to apply\n\n---\n\n## Style editor (palette icon)\n\nAdjust per-item appearance:\n\n- Padding, border width/radius/color\n- Background\n- Text display (where supported)\n- Uses your project color settings\n\n\n\n\n"},"dashboard/explorable":{"title":"Make Data Explorable","category":"Dashboards","slug":"dashboard/explorable","blurb":"Allow viewers to open charts and explore underlying data (feature flag).","order":11,"filename":"explorable.md","uid":"dashboard/explorable","content":"\n## Explorable dashboards\n\nExplorable lets viewers interact with selected columns behind your Story Dashboard.\n\n1. Open your dashboard\n2. Click **Actions → Manage Publishing**\n3. Turn on **Data Explorable**\n4. Select columns to include (required)\n5. Click **Save Changes**\n\n\n\nNotes:\n- You must publish first; explorable controls are disabled when Unpublished\n- Column choices must exist in your dataset; removed columns cannot be saved\n- On public view, AddMaple loads the explorable dataset from `/api/explorable/:projectId` using a secure upload done during save\n\n\n"},"dashboard/overview":{"title":"Dashboards","category":"Dashboards","slug":"dashboard/overview","blurb":"Create, organize, and share dashboards with pages and items.","order":1,"filename":"overview.md","uid":"dashboard/overview","content":"\n## What is a dashboard?\n\nDashboards let you arrange charts, text, images, and KPIs into shareable pages. Use them to tell a story, publish findings, and keep stakeholders aligned.\n\n\n\n---\n\n## Key concepts\n\n- **Dashboard**: A collection of pages you edit in the dashboard editor.\n- **Page**: A canvas of items; tabs can be reordered by dragging.\n- **Item types**: Text, Section, Call Out, Image, Video, and Charts (added from analysis or My Collection).\n- **Manage Publishing**: Opens the Publishing & Sharing modal to publish or make unpublished, copy public link, and set a password.\n- **Explorable data**: Optional setting in the same modal; select columns viewers can explore.\n\n---\n\n## Typical workflow\n\n1. **Create** a dashboard (via Save/Add to Dashboard flow or duplicate an existing one)\n2. **Add items**: Text, Section, Call Out, Image, Video; add Charts via analysis screens or My Collection\n3. **Arrange** items by dragging/resizing on the grid; send to top/bottom when needed\n4. **Add pages** and reorder tabs by dragging; move items to another page via the item menu\n5. **Style** items with the Style Editor (palette icon)\n6. **Manage Publishing** to publish, copy link, and optionally set a password\n7. Enable **Explorable data** and select columns if you want viewers to explore\n\nSee the rest of the Dashboard docs for detailed steps: Create, Add items, Edit items, Arrange items, Pages, Publish, Password, Explorable, Copy & paste, and Styles.\n\n\n"},"dashboard/pages":{"title":"Pages","category":"Dashboards","slug":"dashboard/pages","blurb":"Add, rename, reorder, and move items between pages.","order":7,"filename":"pages.md","uid":"dashboard/pages","content":"\n## Manage pages\n\nUse the page tabs row at the top of the editor.\n\n\n\n---\n\n## Add and rename\n\n1. Click **Add page**\n2. Enter a name (e.g. Overview, Deep dive, Appendix)\n3. Click a page tab to switch between pages\n\n---\n\n## Reorder pages\n\n- Drag page tabs to reorder; release to save the new order\n\n---\n\n## Move items between pages\n\n- Use the item toolbar → **Move to Page** to move an item\n\n\n"},"dashboard/password":{"title":"Password Protection","category":"Dashboards","slug":"dashboard/password","blurb":"Protect a published dashboard with a password (if enabled for your account).","order":10,"filename":"password.md","uid":"dashboard/password","content":"\n## Add or change a password\n\nPassword protection is part of the Publishing & Sharing modal.\n\n1. Click **Actions → Manage Publishing**\n2. Select **Publish with password**\n3. Enter a password (or update it later)\n4. Click **Save Changes**\n\n\n\nYou can remove the password by switching to a public publish type, or keep it private and update the password at any time.\n\n\n"},"dashboard/publish":{"title":"Publish a Dashboard","category":"Dashboards","slug":"dashboard/publish","blurb":"Publish your dashboard to a public link and share it.","order":9,"filename":"publish.md","uid":"dashboard/publish","content":"\n## Publish\n\nPublishing creates a public URL. All controls live in the Publishing & Sharing modal.\n\n1. Open your dashboard\n2. Click **Actions → Manage Publishing**\n3. Choose one of: **Unpublished**, **Publish on AddMaple.com** (public), **Publish with password** (private)\n4. Click **Save Changes**\n\n\n\n---\n\n## Share the link\n\nAfter publishing, a **Public Link** field appears with a **Copy** button.\n\n---\n\n## Unpublish\n\nSwitch back to **Unpublished** and **Save Changes**. The public link stops working immediately.\n\n\n"},"dashboard/styles":{"title":"Styles","category":"Dashboards","slug":"dashboard/styles","blurb":"Control padding, borders, backgrounds, and colors for dashboard items.","order":8,"filename":"styles.md","uid":"dashboard/styles","content":"\n## Style items\n\nUse the palette icon on each item to open the Style Editor.\n\n- **Padding**: Inner spacing\n- **Border**: Width, color, radius\n- **Background**: Solid or transparent\n- **Text style**: Where supported (e.g., text items)\n\n\n\n---\n\n## Use brand colors\n\nStyles respect your project color settings (category/sentiment presets). Set these in **Project Settings → Manage Project**.\n\n---\n\n## Presets and consistency\n\n- Keep spacing consistent using the grid snap\n- Use headings (Section items) to create visual rhythm\n- Prefer the project's primary color for accents\n\n\n"},"data-types/create-segment":{"title":"How to create custom columns/variables","category":"Data Types","slug":"data-types/create-segment","blurb":"Create custom columns/variables to build new data slices—exclusive (one per row) or overlapping (multiple per row)—and explore them instantly.","order":8,"filename":"create-segment.md","uid":"data-types/create-segment","content":"# How to create custom columns/variables\n\nAddMaple allows you to create new columns with custom categories or segments. These can be as simple or as complex as you need. You can create fine-grained personas from multiple filters or just create a simple single filter category.\n\nClick the \"More\" menu and select \"Custom Column/Variable\"\n\nThis will open the \"Create a new Custom Variable or Column\" screen. First give your new column a name.\n\nNow choose if categories overlap - exclusive or overlapping.\n\n### To overlap or not?\n\nAddMaple supports two modes for custom columns. \n\n1. **Exclusive (no overlaps between categories)** - in this mode each category is distinct from the other. This means that we calculate each category one by one and ensure that a record is only added to the first category that it matches. This is the most common way of working and the end result is equivalent to a \"multiple choice\" column.\n\n1. **Overlapping (categories can overlap)** - in this mode, categories can overlap. This is useful if you are comparing multiple personas that are not completely distinct. The end result of this is equivalent to a \"multi-select\" column where each record can be assigned to multiple categories. \n\nIn exclusive mode you will notice that there is a special category at the end with the default name \"Default\". This category contains all records that weren't matched by any of the categories. If you want to ignore these records in your analysis you can simply filter them out when pivoting and exploring. \n\nNow build your categories. As you add data rules, AddMaple will recalculate the number of matched records for each category in real time. Any records not matched will be added to the final \"Default\" category. \n\nAdd as many categories as you need by clicking the \"Add Category\" button. When you have finished, click \"Create Column\".\n\nYour new custom column will appear at the top of your Chart Dashboard. You can now explore, run statistical calculations against it and filter by it."},"data-types/custom-bins":{"title":"How to create custom bins","category":"Data Types","slug":"data-types/custom-bins","blurb":"Define fixed bins for numeric or date data using column settings or custom columns when automatic binning isn't what you need.","order":6,"filename":"custom-bins.md","uid":"data-types/custom-bins","content":"# How to create custom bins\n\nAddMaple automatically calculates appropriate \"bins\" or groups for numeric and date data. These are re-calculated automatically based on your dataset and the filters you have applied.\n\nSometimes it's useful to have your own specific bins that don't change. There are two ways to create custom bins:\n\n## Method 1: Column Settings (Recommended)\n\nFor numeric and date columns, you can configure binning directly in the column settings. This is the easiest way to customize how your data is grouped.\n\n1. **Click on the column header** of a numeric or date column\n2. **Select \"Column Settings\"** from the dropdown menu\n3. **Scroll to the \"Binning\" section**\n\n### For Numeric Columns\n\nYou'll see several binning options:\n\n- **Auto**: Uses optimal binning with Freedman-Diaconis rule\n- **Equal Frequency**: Each bin contains similar numbers of data points\n- **Fixed Width**: Bins have consistent width you define\n- **Custom**: Define your own bin boundaries manually\n\nThe interface shows a live histogram preview so you can see how your data will be grouped before applying changes.\n\n### For Date Columns\n\nYou'll see these binning options:\n\n- **Auto**: Automatically creates optimal time-based bins\n- **Calendar Periods**: Groups by natural boundaries (year, quarter, month, week, day, hour)\n- **Fixed Intervals**: Creates bins of fixed duration (e.g., every 7 days)\n- **Custom Breakpoints**: Define your own date/time boundaries\n\n## Method 2: Custom Column/Variable\n\nFor more complex binning needs or when you want to combine multiple columns, use the Custom Column/Variable feature.\n\nFirst, click on the \"More\" menu and select \"Custom Column/Variable\"\n\n\nGive your new column a name, in this example we are creating an **Age Category** column. Now create your bins (categories) using data rules. In this example we've created 3 age category segments. \n\n\nAfter creating the column, you will have a new column with your custom bins. You can now explore, pivot and filter by this column.\n\n\n## When to Use Each Method\n\n**Use Column Settings** when:\n- You want to modify how an existing numeric or date column is binned\n- You need simple, straightforward binning configurations\n- You want to see live previews of your binning changes\n\n**Use Custom Column/Variable** when:\n- You need to combine multiple columns for complex binning logic\n- You want to create overlapping categories\n- You need more control over category names and organization\n- You want to create bins based on conditional logic across multiple fields"},"data-types/custom-multi-select":{"title":"Create a custom multi-select (all that apply) column","category":"Data Types","slug":"data-types/custom-multi-select","blurb":"Use Custom Column/Variable to manually create an overlapping multi-select column when automatic detection isn't possible.","order":7,"filename":"custom-multi-select.md","uid":"data-types/custom-multi-select","content":"# Create a custom multi-select (all that apply) column\n\nAddMaple has an intelligent engine for detecting multi-select columns, however it is not possible to always detect this accurately.\n\nIf AddMaple hasn't detected and merged a group of columns into a single \"multi-select\" column then you can use the \"Custom Column/Variable\" feature.\n\n \n\nIf you have many columns on your dashboard with only one category showing 100% then it is likely you need to follow this workflow.\n\n\nFrom the \"More\" menu, click \"Custom Column/Variable\"\n\n\nMake sure to select \"Overlapping (categories can overlap)\" in the dropdown on the right. This will allow the resulting column to have more than one value for each row—which is how multi-select or \"all that apply\" columns work. \n\n\nAdd categories for each option for your multi-select column. In this example we have created 3 categories for 3 columns. The result will be a new column where we see the \"Category A\", \"Category B\" and \"Category C\" options in the same column.\n\n\nAfter setting up your column, click \"Create Column\". A new column will be created, ready to pivot and explore."},"data-types/grouped-likert":{"title":"Grouped Opinion Scale Charts","category":"Data Types","slug":"data-types/grouped-likert","blurb":"Learn how grouped opinion scale charts work—adjust groups, reorder or hide options, and switch between chart and table.","order":5,"filename":"grouped-likert.md","uid":"data-types/grouped-likert","content":"# Grouped Opinion Scale Charts\n\nWhere AddMaple detects multiple opinion scale columns next to each other we group them together.\n\nBy default we align the charts on neutral, however you can align on the left if you prefer.\n\n\n\n\n**Adjusting Groups**\n\nIf you want to change which group of columns you are looking at, you can do so via the \"grouped with\" option\n\n\n\n\n**Ordering and Hiding**\n\nIf you want to adjust the order of opinion scale questions (we don't always get it right!), then use the arrows to adjust options up and down. You can also hide options, for example to only show extremes in the chart:\n\n\n\n\n**Viewing Numbers and Averages**\n\nUse the toggles on the left to show numbers on the chart or to add in a bar for \"average\".\n\n\n\n\n**Table View**\n\nWhile AddMaple is visual-first, you can also swap the chart view for a more traditional table (cross-tab).\n\n\n"},"data-types/likert-single":{"title":"Opinion Scale Columns","category":"Data Types","slug":"data-types/likert-single","blurb":"See how to view opinion scale data as Likert charts by pivoting or grouping similar columns.","order":4,"filename":"likert-single.md","uid":"data-types/likert-single","content":"# Opinion Scale Columns\n\nWhen you expand an opinion scale column it will be displayed as a standard AddMaple bar chart.\n\nIf you would like to view it as a Likert scale chart, you will need to either [pivot by another column](../sentence-builder/addpivot) or [group with similar columns](../pivot-chart-and-table/grouping-columns).\n\n \n\n**Pivot By Another Column**\n\nTo pivot by another column:\n\n1. Select another column (either from the related columns table, or by clicking the **Pivot** button at the top of the screen)\n\n1. By default the Opinion Scale column will stay on the left; to get a Likert scale chart you will need to swap the columns - see the video below\n\n\n\n\n**Group With Similar Columns**\n\nIf there are similar columns in your dataset (columns with the same opinion scale answers), then you can group them together with your selected column. This is possible via the \"Group Columns\" option from the More menu. If you can't see the column you'd like to group with then please contact support - by default AddMaple filters down to only the relevant columns able to be grouped. Learn more about [managing column groups](../preparation/manage-columns).\n\n\n"},"data-types/multi-select":{"title":"Multi-Select","category":"Data Types","slug":"data-types/multi-select","blurb":"Learn how multi-select (select-all-that-apply) columns work and how to explore, filter, and pivot them in AddMaple.","order":3,"filename":"multi-select.md","uid":"data-types/multi-select","content":"# AddMaple Help\n\n# Data Types\n\n### Multi-Select\n\nOur multi-select data type is for columns where there can be more than one result. This could be a \"select all that apply\" question in a survey, or a set of tags exported from a database.\n\nIn some data exports this data type is spread over multiple columns. AddMaple will automatically detect this and show the values in a single column. You can also [manually combine columns](../preparation/combining-columns) if needed.\n\nOn the Chart Dashboard, multi-select columns show up with blue bars.\n\n\nWhen you click on a multi-select column you will be taken to the pivot chart view. Here you can see the number of times each category was chosen in the bar chart, along with statistics on the right. In this example the median number of categories per response was 3, with a maximum of 9.\n\n\nIn the table view you can see each category that was selected per row. You can click on a category to filter by it. Learn more about [filtering your data](../frequently-asked-questions/filter-your-data).\n\n"},"data-types/multiple-choice":{"title":"Multiple Choice","category":"Data Types","slug":"data-types/multiple-choice","blurb":"Learn how to explore, filter, and pivot standard single-answer categorical columns in AddMaple.","order":2,"filename":"multiple-choice.md","uid":"data-types/multiple-choice","content":"# Multiple Choice\n\nThis is the main categorical column type that we have in AddMaple. It will show up with turquoise bars in the chart dashboard \n\nMultiple Choice columns on the Chart Dashboard have turquoise bars, you can click on the tile to expand.\n\n\nWhen viewing a pivot chart for a multiple choice column you will see a horizontal bar chart for all the categories, with some stats on the right. \n\n\nIf you hover over one of the bars and select \"Filter\", you will add a filter for that category. You can add additional categories to your filter from the sentence bar at the top of your screen.\n\n\nIn the table view you will see the category per row. You can click on a category to add it as a filter. \n"},"data-types/numeric-data-type":{"title":"Numeric","category":"Data Types","slug":"data-types/numeric-data-type","blurb":"Learn how AddMaple bins numeric data automatically and how to filter and aggregate numeric columns for fast insight.","order":1,"filename":"numeric-data-type.md","uid":"data-types/numeric-data-type","content":"# Numeric\n\nAddMaple detects numeric data and automatically creates bins/buckets so that you can visualize the data in a histogram.\n\n \n\nNumeric columns will show up in green on the chart dashboard.\n\n\nWhen you click on a numeric column, you will be taken to a pivot chart with relevant stats on the right.\n\n\nAddMaple will divide your data into between 8 and 10 groups. This happens automatically and will adjust dynamically based on the filters that you have set. If you would like to create your own custom groups (bins/buckets) you can [create a segmented column](custom-bins).\n\nYou can click on a bar in the chart to filter your dataset. AddMaple will automatically calculate new groups for your numeric data.\n\n\nNumeric columns can also be used to aggregate other columns. For example this chart shows median compensation by work situation. \n"},"frequently-asked-questions/analyse-your-data-from-a-file":{"title":"Analyze Your Data From A File","category":"Frequently Asked Questions","slug":"frequently-asked-questions/analyse-your-data-from-a-file","blurb":"AddMaple automatically analyzes your data from a file and generates charts for you.","order":2,"filename":"analyse-your-data-from-a-file.md","uid":"frequently-asked-questions/analyse-your-data-from-a-file","content":"# Analyze Your Data From A File\n\n### How To AddMaple automatically analyzes your data from a file and generates charts for you. \n\nWe support CSV, XLSX and JSON files. If you have your data in another format, please convert it to CSV in order for us to analyze it.\n\n### 1. Sign In\n\nSign in via the top right \"Sign In\" link using either your Google account or a username and password.\n\n### 2. Select a file for AddMaple to analyze from either\n\n- Your computer: CSV, JSON or XLSX\n\n- A URL: CSV, JSON or XLSX file embedded in a URL\n\n- Survey platforms: Connect directly to [Typeform](/help/integrations/typeform), [SurveyMonkey](/help/integrations/surveymonkey), or [Tally](/help/integrations/tally) - no need to download your survey first\n\n\n\nClick \"Select a file from your computer\". This will bring up a file chooser screen that will allow you to navigate the file system to find a file to read and analyze.\n\nOnce you have selected a file, AddMaple will immediately start reading and analyzing it. This could take a few seconds depending on how large your file is.\n\n**Please note, your data is never uploaded to AddMaple, it stays on your computer**\n\n### Step 3. Explore your data\n\nOnce AddMaple has read your file you will see the explore screen:\n\n\n\nThis screen show some statistics on your data file. In the example above AddMaple found 61 columns and 64,461 rows. The reading and analysis took 7.95 seconds.\n\nYou can now start exploring your data, pivoting, filtering and creating shareable reports.\n\nIf there is a problem reading your file or if it looks like AddMaple hasn't understood your data, please click the \"?\" icon in the bottom right and send us a message.\n\n"},"frequently-asked-questions/analyze-pew-research":{"title":"Analyze Pew Research data","category":"Frequently Asked Questions","slug":"frequently-asked-questions/analyze-pew-research","blurb":"Yes. Pew Research publish their datasets as SAV (SPSS) files. AddMaple can open and analyze them—no SPSS required.","order":1,"filename":"analyze-pew-research.md","uid":"frequently-asked-questions/analyze-pew-research","content":"# Analyze Pew Research data\n\nYes. [Pew Research Center](https://www.pewresearch.org/) publish many of their datasets for free download in SAV (SPSS) format. AddMaple can open and analyze these files without IBM SPSS.\n\n- [Analyze SAV or SPSS files](/help/guides/analyze-sav-or-spss-files) — quick steps to open and explore SAV files in AddMaple \n- [Open .sav files without SPSS](/help/frequently-asked-questions/open-sav-files-without-spss) — convert to CSV, other options, and more detail\n"},"frequently-asked-questions/filter-your-data":{"title":"Filter your data","category":"Frequently Asked Questions","slug":"frequently-asked-questions/filter-your-data","blurb":"AddMaple supports powerful instant filters that are applied across your entire dataset. Filters can be applied directly from charts.","order":3,"filename":"filter-your-data.md","uid":"frequently-asked-questions/filter-your-data","content":"# Filter your data\n\n### How To AddMaple supports powerful instant filters that are applied across your entire dataset.\n\nThere are many ways of adding filters in AddMaple:\n\n### 1. By clicking the \"Filter\" button\n\nFrom the summary, chart, table or raw data views click the **Filter** button at the top of the screen (you can also press \"/\" on your keyboard to open the filter menu).\n\n\n\nClick on the **Filter** button and a new menu will appear asking you to choose which column you would like to filter by\n\n\n\nNote that the actual column names will be the names that AddMaple has detected from your data.\n\nChoose a column (you can use your keyboard to help find a column quicker).\n\nYou will see that before each column name is an icon that shows the column type. For example in the above image most of the columns are \"MC\" - which means \"multiple choice\". Please [see here](which-column-types-are-detected) for more info on the different column types that AddMaple detects.\n\nOnce you have chosen a column you will be able to choose how to filter. The options you get depend on the column type. For example \"MC\" columns will let you filter for rows which match or don't match a certain value. Numeric columns allow you to search using \"greater than\", \"less than\" or \"between\".\n\n\n\nOnce you have chosen the value to filter by, AddMaple instantly filters the data.\n\n \n\n### 2. From a chart\n\nWhen you explore a particular column, you can filter by hovering over the chart:\n\n\n\nIn the above chart, hovering over the \"Student, full-time\" bar, brings up a small box that has a \"Filter by this value\" link.\n\nClicking on that link, will immediately add a filter for that value.\n\n### 3. From a date chart\n\nYou can filter to a specific date range by clicking the relevant bar on a date chart:\n\n\n\n### 4. From the table view\n\nWhen you are in the table view, you can click on any of the MC+ or MC values in a row to automatically filter by them:\n\n\n\n \n"},"frequently-asked-questions/how-do-i-clean-or-recode-response-options":{"title":"How Do I Clean Or Recode Response Options","category":"Frequently Asked Questions","slug":"frequently-asked-questions/how-do-i-clean-or-recode-response-options","blurb":"To clean or recode response options in AddMaple, you have three main methods: using **Clean with AI**, manually editing categories in the **Legend**, or creating a **custom variable/column**.","order":5,"filename":"how-do-i-clean-or-recode-response-options.md","uid":"frequently-asked-questions/how-do-i-clean-or-recode-response-options","content":"# How Do I Clean Or Recode Response Options\n\nTo clean or recode response options in AddMaple, you have three main methods: using **Clean with AI**, manually editing categories in the **Legend**, or creating a **custom variable/column**. Each method suits different needs depending on how much automation or control you want.\n\n---\n\n## 1. Clean or Recode Categories Using **Clean with AI**\n\nThis feature automatically standardizes category labels by renaming, reordering, and optionally merging similar categories.\n\n### Steps:\n1. Open the **Legend** for the column you want to clean:\n - In a pivot chart, click the **Legend** tab on the right.\n - Or in [**Manage Column(s)**](/help/preparation/manage-columns), open the column details and scroll to the **Legend** tab.\n\n2. Click [**Clean categories with AI**](/help/legend/clean-with-ai).\n\n3. In the dialog:\n - Tick **Allow Category Merging** if you want the AI to merge near-duplicate categories.\n - Add **Additional instructions** to guide the AI (e.g., \"Keep age categories in ascending order\" or \"Do not merge 'Other' with anything else\").\n\n4. Click **Start** to generate suggestions.\n\n5. Review the AI’s suggestions for renaming, reordering, and merging.\n\n6. Choose which suggestions to accept.\n\n7. Click **Apply** and then **Save** your changes.\n\n8. Optionally, click **View Mappings** in the legend to see how original categories map to new ones.\n\n**Notes:**\n- Changes persist project-wide and carry through to exports.\n- You can reset to original categories anytime.\n\n---\n\n## 2. Manual Recoding and Merging in the **Legend**\n\nYou can manually adjust categories without AI assistance.\n\n### You can:\n- Rename categories by clicking on their names.\n- Reorder categories by dragging or using the reverse order button.\n- Merge categories by selecting multiple categories and clicking **Merge**. See [How to merge categories](/help/legend/merging-categories) for detailed steps.\n- Hide or show categories.\n- Assign colors to categories. Learn more about [color presets](/help/preparation/colors).\n\nAll manual changes apply across the project and affect exports.\n\n---\n\n## 3. Create a Custom Variable/Column for Recoding\n\nIf you want to create a new variable based on recoded or combined categories, you can create a custom column:\n\n- Use [**Manage Column(s)**](/help/preparation/manage-columns) to create a new column derived from existing data.\n- This is useful for complex recoding or [combining multiple columns into one](/help/preparation/combining-columns).\n- Custom columns can have their own legends and category settings.\n\n---\n\n## Summary\n\n**Clean with AI**\n- **What it does**: Auto rename, reorder, merge\n- **When to use**: Quick, AI-assisted cleaning of messy labels\n\n**Manual Legend Editing**\n- **What it does**: Rename, reorder, merge manually\n- **When to use**: Fine control or small adjustments\n\n**Custom Variable/Column**\n- **What it does**: Create new recoded variable\n- **When to use**: Complex recoding or combining multiple columns\n\n---\n\nThis process helps you standardize messy labels, fix inconsistent capitalization, merge duplicates, and order scales logically.\n\nFor detailed instructions with screenshots, see the **Clean with AI** and **Legend** guides in AddMaple documentation .\n\n## Further Reading\n\n- [How to use Clean with AI](/help/legend/clean-with-ai)\n- [How to work with legends](/help/legend/legend)\n- [How to merge categories](/help/legend/merging-categories)\n- [How to use color presets](/help/preparation/colors)"},"frequently-asked-questions/how-do-i-upload-my-survey-data-into-addmaple":{"title":"How Do I Upload My Survey Data Into AddMaple","category":"Frequently Asked Questions","slug":"frequently-asked-questions/how-do-i-upload-my-survey-data-into-addmaple","blurb":"To upload your survey data into AddMaple, follow these steps: 1.","order":4,"filename":"how-do-i-upload-my-survey-data-into-addmaple.md","uid":"frequently-asked-questions/how-do-i-upload-my-survey-data-into-addmaple","content":"# How Do I Upload My Survey Data Into AddMaple\n\nTo upload your survey data into AddMaple, follow these steps:\n\n1. **Supported File Types**: Prepare your survey data file in one of the supported formats:\n - CSV\n - Excel (`.xlsx`, `.xls`)\n - SPSS (`.sav`)\n - Exports from most survey tools like Qualtrics, SurveyMonkey, Typeform, Google Forms\n\n No reformatting is required before upload.\n\n2. **Start a New Project**:\n - Sign in to AddMaple.\n - Go to the \"New Project\" page.\n\n3. **Select Your Data File**:\n - Click \"Select a file from your computer\".\n - Choose your survey data file (CSV, Excel, SPSS, etc.) from your local drive.\n - Alternatively, you can upload from a URL or connect directly to survey platforms like Typeform, SurveyMonkey, or Tally.\n\n4. **Automatic Data Processing**:\n - AddMaple will scan your file headers and sample data.\n - It automatically assigns column types (numeric, categorical, multi-select, text, date, boolean).\n - It merges columns that belong to one question but were exported as multiple columns (common in single-select and multi-select questions).\n - It groups related columns (e.g., Likert scales).\n - Generates readable names for merged/grouped items.\n\n5. **Review and Adjust Columns (Optional)**:\n - Open **Manage columns** to review how AddMaple interpreted your data.\n - You can rename columns, change types, merge or unmerge columns, group or ungroup columns, and hide/unhide columns.\n - This step is useful if your survey export is messy or if you want to customize data presentation.\n\n6. **Explore Your Data**:\n - Once uploaded and processed, you can start exploring your data with pivots, filters, and charts.\n\n**Notes**:\n- Your data is processed locally in your browser and is never uploaded to AddMaple's servers.\n- SPSS `.sav` files can be opened directly without needing SPSS software.\n\nThis process is designed to get you analyzing your survey data quickly and easily without needing to reformat or preprocess your files manually.\n\nFor detailed examples and screenshots, see the \"Importing and Preparing Data in AddMaple\" and \"Analyze Your Data From A File\" guides in the documentation .\n\n## Further Reading\n\n- [Importing and Preparing Data in AddMaple](/help/preparation/importing-and-preparing-data)\n- [Typeform](/help/integrations/typeform)\n- [SurveyMonkey](/help/integrations/surveymonkey)\n- [Tally](/help/integrations/tally)\n"},"frequently-asked-questions/how-does-addmaple-pricing-work":{"title":"How does AddMaple pricing work?","category":"Frequently Asked Questions","slug":"frequently-asked-questions/how-does-addmaple-pricing-work","blurb":"Learn about AddMaple's pricing plans, how to upgrade from free to paid plans, and special pricing for NGOs, academia, and students.","order":14,"filename":"how-does-addmaple-pricing-work.md","uid":"frequently-asked-questions/how-does-addmaple-pricing-work","content":"\n# How does AddMaple pricing work?\n\nAddMaple offers flexible pricing plans to suit different needs, from individual researchers to large organizations. Here's everything you need to know about our pricing and upgrade process.\n\n## Available Plans\n\n### Free Plan\n- **Cost:** Free forever\n- **Limits:** Up to 100 rows and 12 columns\n- **Includes:** Full access to all AddMaple features within the limits\n- **Perfect for:** Trying AddMaple, small datasets, or basic analysis\n\n### Starter Plan\n- **Cost:** $59/month or $599/year (save 15%)\n- **Includes:** Everything in Free, plus unlimited data, auto data cleaning, pivoting & filtering, interactive Story Dashboards, PowerPoint export, and AI explanations\n- **Perfect for:** Individual analysts who need to analyze larger datasets\n\n### Professional Plan\n- **Cost:** $169/month or $1,500/year (save 26%)\n- **Includes:** Everything in Starter, plus AI thematic analysis, AI Agent, full statistical analysis (significance tests, key drivers, regression), and public data scraping\n- **Perfect for:** Researchers and analysts who need advanced analytics and AI-powered insights\n\n### Business Plan\n- **Cost:** Contact us for custom pricing\n- **Includes:** Everything in Professional, plus team collaboration, private dashboards, Excel exports, multi-file projects, clustering, and custom integrations\n- **Perfect for:** Teams, agencies, and organizations with complex data analysis needs\n\n## How to Upgrade\n\n### From Free to Paid Plans (Starter or Professional)\n\n1. **Sign up for AddMaple** with your free account\n2. **Look for the upgrade button** simply create a project and you will see the upgrade or \"Choose Plan\" button\n3. **Click the upgrade button** to see available paid plans\n4. **Choose your plan** (Starter or Professional)\n5. **Select billing frequency** (monthly or annual)\n6. **Enter payment details** (credit card or PayPal)\n7. **Start analyzing** with unlimited data immediately\n\nThe upgrade process is instant—you'll have access to all features as soon as payment is processed.\n\n### For Business Plans\n\nBusiness plans require a custom setup process:\n\n1. **Visit** [addmaple.com/setup](https://addmaple.com/setup)\n2. **Schedule a call** with our team\n3. **Discuss your needs** and get a custom quote\n4. **Complete setup** with dedicated onboarding support\n\n## Special Pricing Programs\n\n### NGOs — 50% Off Annual Plans\n- **Eligibility:** Registered nonprofits\n- **Discount:** 50% off Starter, Professional, or Business annual plans\n- **Apply at:** [addmaple.com/impact](https://addmaple.com/impact)\n\n### Academic License — $2,000/year\n- **Eligibility:** Departments, labs, and classes\n- **Includes:** Up to 10 named users on Professional plan\n- **Extras:** Guided first-project session\n- **Apply at:** [addmaple.com/impact](https://addmaple.com/impact)\n\n### Student Plan — $99/year\n- **Eligibility:** Individual students\n- **Includes:** All Professional plan features\n- **Limitations:** For coursework only (not commercial work)\n- **Apply at:** [addmaple.com/impact](https://addmaple.com/impact)\n\n## Payment Methods\n\n- **Credit cards:** Visa, MasterCard, American Express\n- **PayPal:** Direct PayPal payments\n- **Purchase orders:** Available for Business and Academic plans\n\n## Billing and Currency\n\n**Paddle is our merchant of record** - All payments are processed securely through Paddle, a trusted payment processor that handles billing, invoicing, and payment processing for thousands of software companies worldwide.\n\n**Local currency billing** - Paddle automatically detects your location and bills you in your local currency (USD, EUR, GBP, CAD, AUD, etc.) for your convenience. Prices may vary slightly based on exchange rates and local taxes.\n\n## Billing and Cancellation\n\n- **Billing:** Monthly or annual billing available\n- **Cancellation:** Cancel anytime from your [account settings](/app/profile)\n\n\n"},"frequently-asked-questions/how-does-addmaple-use-openai":{"title":"How does AddMaple use OpenAI?","category":"Frequently Asked Questions","slug":"frequently-asked-questions/how-does-addmaple-use-openai","blurb":"Learn how we use OpenAI, but how your data is not stored or used for training new models.","order":7,"filename":"how-does-addmaple-use-openai.md","uid":"frequently-asked-questions/how-does-addmaple-use-openai","content":"# How does AddMaple use OpenAI?\n\n### FREQUENTLY ASKED QUESTIONSAddMaple uses [OpenAI](https://openai.com/) to power some of it's AI features. These features are entirely optional & before using them we will ask for your explicit consent to send data to OpenAI (you can remove this consent from your [profile](https://addmaple.com/app/profile) page)\n\nIf you do decide to use these features then please note that we are using OpenAI's API which has two distinct differences from the consumer ChatGPT:\n\n1. Your data is not stored by OpenAI. Any data you choose to analyze with AI will be sent to OpenAI, but will not be stored by them. Neither is the data stored by AddMaple. Your data remains on your system.\n\n1. Your data is not used for training new OpenAI models. While by default conversations that you have using ChatGPT can be used for training purposes, this is not true for data sent under the commercial license that we have with OpenAI.\n\nIf you have any questions about this, please don't hesitate to contact our support team.\n\n "},"frequently-asked-questions/how-does-addmaple-work-without-uploading":{"title":"How does AddMaple work without uploading data?","category":"Frequently Asked Questions","slug":"frequently-asked-questions/how-does-addmaple-work-without-uploading","blurb":"AddMaple analyses your data in your browser without uploading it to the cloud. We use modern web APIs to read and process your files all within your browser.","order":11,"filename":"how-does-addmaple-work-without-uploading.md","uid":"frequently-asked-questions/how-does-addmaple-work-without-uploading","content":"# How does AddMaple work without uploading data?\n\n### Data analysis in your own browserAddMaple is lightning fast because it doesn't upload your data, but rather processes it locally on your computer.\n\nWe use modern web APIs such as the [File API](https://developer.mozilla.org/en-US/docs/Web/API/File) and [Worker API](https://developer.mozilla.org/en-US/docs/Web/API/Worker) to read your file without sending it to our servers in the cloud. We convert the data into a proprietary column store designed for very fast pivoting, binning and filtering of data.\n\nBy keeping data local to your browser, you have increased privacy as you are not sharing your data, and the performance of the tool on modern computers far exceeds cloud based solutions.\n\nEven SPSS files are read locally in your browser and are not uploaded to the cloud - data sets like the World Values Survey with 600,000+ records are read in just a few seconds.\n\nWe have a Fully Offline version of AddMaple in development, please contact us for more details. Especially for the Jameses out there, you know who you are :). \n\n \n\n \n\n "},"frequently-asked-questions/how-to-pivot-your-data":{"title":"How to pivot your data","category":"Frequently Asked Questions","slug":"frequently-asked-questions/how-to-pivot-your-data","blurb":"AddMaple makes it simple and intuitive to pivot your data. We help you cross-tabulate, pivot and aggregate your data without any complicated settings.","order":6,"filename":"how-to-pivot-your-data.md","uid":"frequently-asked-questions/how-to-pivot-your-data","content":"# How to pivot your data\n\n### Pivoting (or cross-tabulating) is at the heart of AddMaple. This article explains how to pivot in AddMaple, if you haven't got an account yet, you can try our [free online pivot tool](https://addmaple.com/tools/online-pivot-table-tool).\n\nAddMaple automatically aggregates your data as soon as it loads. The primary \"explore\" screen shows a per column pivot chart:\n\n\n\nIn the above image there are 3 different column types: *numeric*, *multiple choice* and *multiple choice with multiple answers*. AddMaple has already pivoted on each column, in addition for the numeric column AddMaple has automatically grouped (or binned) the data into sensible groups. For the columns the have multiple results per cell (e.g. \"red,yellow,blue\"), AddMaple has already pre-processed the results - something that is very difficult to do in a spreadsheet.\n\nWhen you click on a chart you will be taken to a larger view of just that column:\n\n\n\nThis expanded view automatically shows 10 groups instead of 5 and has a handy stats panel on the right hand side.\n\nThe real power of pivots in AddMaple is shown when you choose to aggregate by a different column or display multiple columns together.\n\n### Mean, Median and Total\n\nTraditional pivot tables allow you to view averages and totals from different columns using the \"values\" setting. This is simple to do in AddMaple.\n\nThe default setting is \"Number Of\" - this is equivalent to COUNTA in a spreadsheet.\n\n\n\nBy clicking on \"Number of\" you can choose a different aggregation option: \n\n- Total (equivalent to SUM)\n\n- Average (equivalent to AVERAGE)\n\n- Median (equivalent to MEDIAN)\n\nThe real timesaver is that AddMaple has already detected the different column types and therefore only displays numeric columns to aggregate by. Here is an example showing a median aggregation.\n\n\n\nAddMaple instantly calculates the results (even for large datasets) and displays the results in an easy to read chart format. Please read [here](why-do-you-use-horizontal-bar-charts) for details on why we use horizontal bar charts.\n\n### Pivoting by Multiple Columns\n\nTo explore two (or three) columns at the same time, simply click the plus button, select \"Add Pivot\" and choose another column\n\n\n\nOnce you've chosen your new column, AddMaple will instantly show your data as a multi-column pivot chart.\n\n\n\nAddMaple displays the data in a chart so that it is easy to spot trends and understand your data at a glance. You can hover over (or tap on) a chart segment to get the actual values.\n\n\n\n### Percentages rather than absolutes\n\nFor many datasets, it is easier to see trends when comparing percentage values rather than absolute values. AddMaple makes it easy to toggle between percentages and absolutes with a single click.\n\n\n\n### Swapping Columns\n\nSometimes your data will be easier to understand if you swap the order of the columns, i.e. instead of viewing Column A, segmented by Column B - you want to view Column B, segmented by Column A.\n\nTo do this in AddMaple, click on the column you want to swap and there will be a swap option at the top of the select menu\n\n\n\nYou will now be able to see the same data from a different perspective:\n\n\n\nIt's easy to swap backwards and forwards as you explore your data.\n\n### Three Column Pivots\n\nIn large data sets it may be useful to pivot by three columns, to do this in AddMaple, click on the plus button and add another pivot, for example:\n\n\n\n---\n\nHappy pivoting\n"},"frequently-asked-questions/open-sav-files-without-spss":{"title":"Open .sav files without spss","category":"Frequently Asked Questions","slug":"frequently-asked-questions/open-sav-files-without-spss","blurb":"Discover how to open .sav files without SPSS. Convert .sav files to Excel or CSV, and instantly explore and analyze .sav files in the cloud—no IBM SPSS required.","order":10,"filename":"open-sav-files-without-spss.md","uid":"frequently-asked-questions/open-sav-files-without-spss","content":"\n# How to open .sav files without spss\n\n### What is a .SAV / SPSS file\n\n\nA .sav file is a data file typically associated with IBM SPSS (Statistical Package for the Social Sciences). It is frequently used by researchers, including renowned organizations such as [Pew Research](https://www.pewresearch.org/). \n\nDespite its widespread use, the file format is a proprietary binary format which is not compatible with many software applications. For instance, spreadsheet applications like Excel or Google Sheets do not support .sav files natively. \n\nThe .sav files can be opened using [IBM SPSS](https://www.ibm.com/analytics/spss-statistics-software) or an open-source equivalent, named [GNU PSPP](https://www.gnu.org/software/pspp/). However, both these tools have their limitations. IBM software, despite being in existence since 1968, is cumbersome to use and quite costly. On the other hand, the open-source PSPP may not require a fee, but it is also hampered by an outdated and clunky interface. \n\nAddMaple offers a more elegant alternative: open .sav files and analyze them immediately, or export to CSV after opening if you need a spreadsheet-friendly copy. We get you up and analyzing in seconds. AddMaple's intuitive filtering, segmentation and pivoting/cross tabulation features make data analysis fast and dare we say, even fun. Why? Because AddMaple turns columns into a chart dashboard in seconds and allows you to expand charts, click on a bar in a chart to segment by that response, pivot two or more columns for instant comparison across your data set and more. \n\n \n\n### How you can open a .sav file without SPSS\n\n \n\nIf you don't have IBM SPSS, you have a few options to open .sav files:\n\n- **Open directly with AddMaple** — upload your .sav file, analyze in the cloud, and export to CSV if you need a copy for Excel or Google Sheets. This is the quickest way to get from .sav to insights.\n\n- **Use [GNU PSPP](https://www.gnu.org/software/pspp/)** — free, open-source software that can open .sav files and export to CSV. You’ll need to install it and work in its interface.\n\n- **Use [R](https://www.r-project.org/) with the [Haven](https://haven.tidyverse.org/reference/read_spss.html) package** — good if you already use R; you can read .sav and write CSV from there.\n\nFor example, this is the Pew Research [Core Trends Survey](https://www.pewresearch.org/internet/dataset/core-trends-survey/) sav file opened in AddMaple:\n\n\n\nThe dataset contains 1,502 responses with 90 questions per response - it was analyzed and charts were produced for each question in 2.33 seconds.\n\n### How to convert a .sav file to a CSV\n\nA CSV file is a very basic file type that can be opened by many different software packages. A CSV file is less efficient than a .sav SPSS file—the same data will result in a bigger CSV file—but CSV is universal. To convert a .sav file to CSV: open the .sav file in AddMaple and export or download as CSV, or use PSPP or R (with the Haven package) to read the .sav and write a CSV. Once you have a CSV, you can open it anywhere. For more detailed guidance on converting SAV to CSV (including in the browser, no install, with labels extracted), see our [SPSS (SAV) to CSV converter](https://addmaple.com/tools/spss-.sav-to-csv-converter) page.\n\n### How to open a .sav file in Excel or Google Sheets\n\nTo open a .sav file in Excel or Google Sheets you need to first convert it to .csv, since spreadsheet applications don’t support .sav natively. Open your .sav file in AddMaple and export or download as CSV, then open that CSV in Excel, Google Sheets or Numbers. For step-by-step conversion guidance (convert in the browser, download CSV, open in Excel without SPSS), see our [SPSS (SAV) to CSV converter](https://addmaple.com/tools/spss-.sav-to-csv-converter) page. Alternatively, use PSPP or R to convert the .sav to CSV, then open the CSV in your spreadsheet. Either way, you get your .sav data into Excel or Google Sheets without IBM SPSS.\n\n### How can I get cross-tabs and pivots from my sav file\n\nIf you open your sav file in AddMaple or use our [Online Pivot Table Tool](https://addmaple.com/tools/online-pivot-table-tool) you can quickly and intuitively create cross-tabs, segment your data and create beautiful pivot tables and graphs.\n\n**See also:** [Analyze SAV or SPSS files](/help/guides/analyze-sav-or-spss-files) · [Importing and preparing data](/help/preparation/importing-and-preparing-data)\n\n"},"frequently-asked-questions/opening-excel-files":{"title":"How to open excel files in AddMaple","category":"Frequently Asked Questions","blurb":"How to open Excel files in AddMaple, covering multi-sheet files and sheets with multiple headers","order":20,"filename":"opening-excel-files.md","uid":"frequently-asked-questions/opening-excel-files","slug":"frequently-asked-questions/opening-excel-files","content":"# How to Open Excel Files in AddMaple\n\n**Summary:** Learn how to start a new project in AddMaple by uploading Excel files (`.xlsx` or `.xls`). This guide covers sheet selection, headers, file limits, and troubleshooting. \n\n## TL;DR\n- Go to **New Project → Select File** and upload your Excel file. \n- If there are multiple sheets, choose the sheet with **raw data** (not summaries). \n- AddMaple detects headers automatically and prepares the data for analysis. \n\n---\n\n## Step-by-Step Instructions\n\n1. **Start a new project** \n - From the dashboard, click **New Project**. \n - Select **File** and browse to your Excel file (`.xlsx` or `.xls`). \n\n2. **Select a sheet** (if applicable) \n - If your Excel file has multiple sheets, AddMaple will prompt you to select one. \n - Choose the sheet that contains **raw, row-level data**. \n - ⚠️ If you accidentally select the wrong sheet, you’ll need to create a new project to re-import. \n\n3. **Data loading** \n - AddMaple will load your data, automatically clean it, and detect variable types. \n - Headers are identified automatically, even if: \n - There are blank header rows. \n - Survey platforms (e.g. SurveyMonkey) export headers across two rows. \n\n4. **Limits** \n - Supports thousands of variables (columns). \n - Supports hundreds of thousands of rows. \n\n5. **Next steps** \n - Once loaded, you can adjust **grouping, combining, and variable types** in the preparation tools. \n - See [Managing columns](../preparation/manage-columns.md) for details. \n\n---\n\n## Troubleshooting\n\n- **Error opening file:** Some Excel exports may cause problems. If your file does not open: \n - Re-export it as a **CSV with a single header row**. \n - Then re-import into AddMaple. \n\n---\n\n"},"frequently-asked-questions/what-is-the-largest-file-i-can-analyse":{"title":"What is the largest file I can analyze?","category":"Frequently Asked Questions","slug":"frequently-asked-questions/what-is-the-largest-file-i-can-analyse","blurb":"AddMaple can read large data files - including files that will crash a spreadsheet. On a modern computer AddMaple can easily read in data files of up to 200MB...","order":9,"filename":"what-is-the-largest-file-i-can-analyse.md","uid":"frequently-asked-questions/what-is-the-largest-file-i-can-analyse","content":"# What is the largest file I can analyze?\n\n### Frequently Asked QuestionsAddMaple can read large data files - including files that will crash a spreadsheet.\n\nOn a modern computer AddMaple can easily read in data files of up to **200MB** with **millions of rows** of data. If your data is larger than this then AddMaple may still be able to read the data but it will depend on how much memory your computer has.\n\nAddMaple uses a custom column-based in-memory store to allow instant access and analysis of your data, but this requires loading the entire file into memory. This approach works remarkably well for a wide range of data analysis tasks.\n\n "},"frequently-asked-questions/which-column-types-are-detected":{"title":"Which column types are detected?","category":"Frequently Asked Questions","slug":"frequently-asked-questions/which-column-types-are-detected","blurb":"AddMaple detects many different column types automatically including numbers, currency, dates, categories, etc.","order":8,"filename":"which-column-types-are-detected.md","uid":"frequently-asked-questions/which-column-types-are-detected","content":"# Which column types are detected?\n\n### Frequently Asked QuestionsAddMaple automatically detects the following data types.\n\n### Numbers\n\n\n\nDetecting numeric columns is important as AddMaple can use these columns to allow instant aggregations, e.g. of totals, mean or median values. AddMaple can deal with empty rows, \"N/A\" values, numbers formatted as strings, etc. Learn more about [numeric data types](../data-types/numeric-data-type). \n\n### Multiple Choice (Category)\n\n\n\nMultiple choice columns are columns where there are a limited set of text results in the column. This could be the results of a multiple choice question in a survey or it could represent a category in another type of dataset. Learn more about [multiple choice data types](../data-types/multiple-choice).\n\n### Multiple Choice + (Tag)\n\n\n\nMultiple Choice Plus columns are columns where there are multiple results per column. In a survey this is where respondents are allowed to select multiple answers to a single question. In other datasets this could be tags, where a data element could be assigned multiple tags. AddMaple can deal with empty rows, and a variety of techniques for denoting that there are multiple answers - including commas, pipes and semicolons.\n\n### Dates\n\n\n\nDate columns allow us to summarize data with special time based charts. If your date format is not recognized, please let us know.\n\n### Opinion Scale\n\n\n\nAddMaple has special detection for opinion scales. This includes both numeric scales, i.e. 1 to 10, and text based answers, e.g. Very Important, Somewhat Important, etc.\n\nThese columns allow us to display special Likert charts.\n\n### Text\n\n\n\nIf AddMaple detects free text answers in a column it is classed as text. Future improvements to AddMaple will allow full text search for these columns and automated tagging. You can view data in this column in the table or raw data view.\n\n \n\n### Unique\n\n\n\nThese columns have a different value for each row. Typically they are identifiers. AddMaple can't filter or pivot by these columns, but you can view this data in the table or raw data view.\n\n \n\n### Percent\n\n\n\nAddMaple automatically detects percentage columns that contain a number followed by a \"%\" sign. They can be filtered and viewed in the same way as numeric columns.\n\n### Currency\n\n\n\nAddMaple automatically detects currency columns. They can be filtered and viewed in the same way as numeric columns."},"frequently-asked-questions/why-do-you-use-horizontal-bar-charts":{"title":"Why do you use horizontal bar charts","category":"Frequently Asked Questions","slug":"frequently-asked-questions/why-do-you-use-horizontal-bar-charts","blurb":"AddMaple is designed to work with any data source - this includes data where column names or items of data may be long, or where there are many possible values for a column.","order":12,"filename":"why-do-you-use-horizontal-bar-charts.md","uid":"frequently-asked-questions/why-do-you-use-horizontal-bar-charts","content":"# Why do you use horizontal bar charts\n\nAddMaple is designed to work with any data source - this includes data where column names or items of data may be long, or where there are many possible values for a column.\n\n\n\nIn the above example, we can see that it is easy to read \"United Kingdom of Great Britain and Northern Ireland\". A vertical layout would make it hard to handle such long pieces of text."},"frequently-asked-questions/why-does-the-stats-summary-say-no-relationship-when-details-show-differences":{"title":"Why does the stats summary say there’s no relationship when details show differences?","category":"Frequently Asked Questions","slug":"frequently-asked-questions/why-does-the-stats-summary-say-no-relationship-when-details-show-differences","blurb":"It’s possible to see a “no significant relationship” summary while still getting meaningful category-level differences and significance shading. Here’s why—and how to interpret it.","order":13,"filename":"why-does-the-stats-summary-say-no-relationship-when-details-show-differences.md","uid":"frequently-asked-questions/why-does-the-stats-summary-say-no-relationship-when-details-show-differences","content":"# Why does the stats summary say there’s no relationship when details show differences?\n\nIt’s not a contradiction. AddMaple runs several complementary tests that answer slightly different questions:\n\n- **Global chi-square (table-level)**: asks “Is there any relationship at all between these two categorical columns?” If assumptions aren’t met (e.g., too many expected counts < 5), we suppress or downweight the result and may show “no significant relationship.”\n- **Category vs. rest analysis (per-category)**: asks “Is this specific category different from all others combined?” This can surface strong differences for individual categories even when the overall table-level test doesn’t clear our thresholds.\n- **Cell-level z-scores with significance shading (per cell)**: asks “Is this specific cell higher or lower than expected?” We color cells based on standardized residuals (z), adjust p-values within each column using Holm-Bonferroni, and apply practical-effect guards so only reliable signals get stronger shading. See [Significance Testing](../stats/significance-testing).\n\n**Important:** Before interpreting results, filter out or merge very small categories to avoid sparse cells (low expected counts). This stabilizes the tests and reduces the chance that the global chi-square is suppressed while finer-grained analyses still show signals. You can merge categories in the [Legend](../legend/merging-categories) or filter to focus on well-populated groups.\n\n## Why the summary can say “no relationship”\n\n- **Assumption checks matter**: The global chi-square requires that at least 80% of expected counts are ≥ 5 and none are < 1 for the usual inference to be valid. If your contingency table has sparse cells (common when segments are granular), we won’t claim a strong table-level relationship.\n- **Different questions, different thresholds**: The per-category and per-cell analyses answer narrower questions and can still show meaningful signals for particular categories or intersections, even when the overall relationship is weak or unstable.\n\n## How to interpret the mixed signals\n\n1. **Start with the summary**: If it says “no significant relationship,” treat the overall linkage as weak/inconclusive—often due to sparse data.\n2. **Check “Further Insights Between Column Categories”**: Use this to identify which specific categories are notably different vs. the rest. These are directional findings you can investigate further.\n3. **Use significance shading in a pivot table**: Turn on [Significance Testing](../stats/significance-testing). Stronger shades indicate reliable, adjusted differences at the cell level. Keep sample sizes in mind; small totals or expected counts can suppress stronger tiers.\n4. **Stabilize the analysis when needed**:\n - Combine/merge very small categories in the [Legend](../legend/merging-categories) or filter to focus on well-populated groups.\n - Consider broader groupings (e.g., recode long tails) to raise expected counts.\n - Verify that you’re comparing categorical vs categorical; numeric vs categorical uses ANOVA/t-tests alongside the z-score table.\n\n## Quick definitions\n\n- **Global chi-square**: Table-level test of any association; summarized in the top “Stats Overview.”\n- **Cramér’s V**: Effect size for chi-square; 0 = none, 1 = perfect.\n- **Category vs. rest**: Per-category test showing which categories drive differences.\n- **Z-score shading**: Per-cell standardized residuals with Holm adjustment and practical-effect guards for reliable highlights.\n\n## Practical takeaway\n\n- You can rely on the per-category and per-cell findings as targeted insights—especially when they pass our adjusted thresholds—even if the table-level summary is conservative due to sparse data. For client documents, describe them as “specific category differences” or “cell-level differences,” not as a blanket relationship between the entire pair of columns.\n\nFor related background, see:\n- [Chi-Square Test](../stats/chi-square)\n- [Exploring Related Columns](../stats/related-columns)\n- [Significance Testing](../stats/significance-testing)\n"},"guides/addmaple-v3":{"title":"AddMaple V3","category":"Guides","slug":"guides/addmaple-v3","blurb":"Welcome to AddMaple V3 — launched Sept 29, 2025. See what’s new and how to get started.","order":0,"filename":"addmaple-v3.md","uid":"guides/addmaple-v3","content":"\n## AddMaple V3\n\nWelcome to AddMaple V3 — launched September 29, 2025. This release brings faster analysis, richer charts, deeper statistics, and a big change to how you manage your data: you can now fully control cleaning and preparation.\n\n### Highlights\n- **You control prep**: Combine/separate columns, group/ungroup, edit types and titles, tidy legends, and use Clean with AI.\n- **New charts**: Box plots, mean dot plots, improved dot (bubble) charts with Fixed vs Auto scale, plus pie/donut/rose and geographic maps.\n- **New stats**: Expanded engine with Chi‑Square, T‑Test, ANOVA, Kruskal‑Wallis, correlations, regression, significance shading, key drivers, and NPS.\n- **Faster by default**: Instant summaries for big files, SAV/SPSS support, and responsive UI.\n- **Dashboards & Insights**: Streamlined Story Dashboards, publish/share with password, explorable data, and better collection-to-dashboard flows.\n\n---\n\n## Data prep you control\n\nYou can now fix what used to be automatic-only. Prepare data precisely the way you need.\n\n- **Manage Columns**: rename, change types, hide/unhide, review merges/groups: see [Manage columns](../preparation/manage-columns).\n- **Combine columns**: merge single/multi-select exports back into one variable; confirm positive/negative values where needed: see [Combine columns](../preparation/combining-columns).\n- **Separate columns**: undo automatic or manual combines when you want originals back: see [Combine columns](../preparation/combining-columns.md#separating-columns).\n- **Group / Ungroup**: organize Likert/matrix questions as logical sets; edit group and item display names: see [Group columns](../preparation/group) and [Grouping from charts](../pivot-chart-and-table/grouping-columns).\n- **Legend control**: rename, reorder, hide/show, merge categories, assign colors, toggle Ordered vs Independent: see [Legend](../legend/legend) and [Ordered vs Independent](../legend/ordered-vs-independent).\n- **Clean with AI**: auto‑standardize labels, order scales, optionally merge near‑duplicates with guardrails: see [Clean with AI](../legend/clean-with-ai).\n- **Custom bins**: fixed numeric/date ranges with live previews: see [Number binning](../preparation/number-binning) and [Date binning](../preparation/date-binning).\n- **Weighting**: apply a weight column; charts, tables, and tests use weighted bases: see [Weighting](../preparation/weighting).\n\n---\n\n## Charts\n\n- **Dot charts (bubble)** with scale control: choose **0–100** (fixed) or **Auto Scale**; ideal for percentage comparisons and grouped pivots: see [Dot charts](../pivot-chart-and-table/bubble-dot-plots).\n- **Box plots & Mean dot plots** for numeric distributions and group comparisons: see [Box plots and mean dot plots](../pivot-chart-and-table/boxplots-mean-dot-plots).\n- **Additional charts** for single‑column exploration: pie, donut, rose; automatic **geographic maps** when location data is detected: see [Additional charts](../pivot-chart-and-table/additional-charts).\n- **Likert charts**: group related opinion scales, align on neutral or left, show numbers/average: see [Grouped Likert](../data-types/grouped-likert) and [Opinion scale columns](../data-types/likert-single).\n\nRelated basics: [Why horizontal bars](../frequently-asked-questions/why-do-you-use-horizontal-bar-charts), [How to pivot](../frequently-asked-questions/how-to-pivot-your-data), [Add a pivot](../sentence-builder/addpivot), [Aggregation](../sentence-builder/aggregation).\n\n---\n\n## Statistics\n\nV3 expands automatic testing and interpretability. You explore, we surface the math.\n\n- **At a glance**: see the summary card on pivot views; click through to full details: see [Statistical calculations](./statisticalcalculations).\n- **Tests (auto‑selected)**:\n - Categorical vs categorical: [Chi‑Square](../stats/chi-square)\n - Numeric vs 2 groups: [T‑Test](../stats/ttest)\n - Numeric vs 3+ groups: [ANOVA](../stats/anovatest) or [Kruskal‑Wallis](../stats/kruskal-wallis) when assumptions are weak\n - Numeric vs numeric: [Correlation (Pearson/Spearman)](../stats/correlation)\n- **Significance shading** inside pivot tables: z‑score tiers, Holm adjustment, practical‑effect guards: see [Significance testing](../stats/significance-testing).\n- **Related columns** view: scan strongest relationships; click to jump to a pivot: see [Related columns](../stats/related-columns).\n- **Regression**: linear and logistic with visuals: see [Regression](../stats/regression).\n- **Key drivers**: random‑forest importance to explain outcomes: see [Key driver analysis](../stats/key-driver-analysis).\n- **NPS**: automatic detection and scoring for 0–10 scales: see [NPS](../stats/nps).\n\n---\n\n## Dashboards, sharing, and Insights\n\n- **Insights (My Collection)**: save analyses, tag, export, and add to dashboards: see [Insights overview](../insights/overview), [Using My Collection](../insights/collection-guide), and [Add to dashboard](../insights/add-to-dashboard).\n- **Story Dashboards**: create pages, add text/sections/images/videos/charts, arrange and style: see [Dashboards](../dashboard/overview), [Create](../dashboard/create), [Add items](../dashboard/add-items), [Arrange](../dashboard/arrange-items), [Edit items](../dashboard/edit-items), [Styles](../dashboard/styles).\n- **Publish & protect**: public link or password: see [Publish](../dashboard/publish) and [Password](../dashboard/password).\n- **Explorable data**: let viewers open charts and explore selected columns: see [Explorable](../dashboard/explorable).\n- **Copy & paste** items across pages/dashboards: see [Copy & paste](../dashboard/copy-paste).\n\n---\n\n## Table and row views\n\n- **Interactive tables**: add/remove columns, sort, filter by clicking values: see [Add/remove columns](../table/addremovetablecol), [Sort](../table/sorttable), [Filter from table](../table/addfiltertable).\n- **Row‑by‑row**: read full responses with context; add filters from rows; quick navigation: see [Understand row view](../row-by-row/understandrow), [Add filter from row](../row-by-row/addfilterrow), [Navigate rows](../row-by-row/navigaterows).\n- **Status line logic**: rows vs results, hiding vs filtering, weighted bases: see [Filtering vs hiding](../pivot-chart-and-table/filtering-vs-hiding).\n\n---\n\n## Data sources and scale\n\n- **Excel**: multi‑sheet support and header handling: see [Open Excel files](../frequently-asked-questions/opening-excel-files).\n- **SAV/SPSS**: open directly, analyze instantly, or convert: see [Analyze SAV or SPSS files](../guides/analyze-sav-or-spss-files) and [Open .sav without SPSS](../frequently-asked-questions/open-sav-files-without-spss).\n- **Big files**: millions of rows on modern machines; everything runs in your browser: see [Largest file size](../frequently-asked-questions/what-is-the-largest-file-i-can-analyse) and [How AddMaple works without uploading](../frequently-asked-questions/how-does-addmaple-work-without-uploading).\n\n"},"guides/analyze-sav-or-spss-files":{"title":"Analyze SAV or SPSS files","category":"Guides","slug":"guides/analyze-sav-or-spss-files","blurb":"AddMaple is one of the few cloud based software tools that can read SPSS (or SAV) data files. They have an unusual format and can't be opened by standard spreadsheets.","order":3,"filename":"analyze-sav-or-spss-files.md","uid":"guides/analyze-sav-or-spss-files","content":"# Analyze SAV or SPSS files\n\nSPSS Statistics is software from IBM that was first released in 1968! It is still commonly used for performing statistical analysis of large datasets, for example survey data.\n\nAddMaple is one of the few cloud based software tools that can read SPSS (or SAV) data files. They have an unusual format and can't be opened by standard spreadsheets. \n\nTo open an SPSS or SAV file, simply go to the \"New Project\" page and select the file from your computer. AddMaple will open and instantly analyze your data.\n\n[Pew Research](https://www.pewresearch.org/) publish their datasets in this format. With AddMaple you can explore the raw data quickly and easily.\n\n**See also:** [Open .sav files without SPSS](/help/frequently-asked-questions/open-sav-files-without-spss) — convert to CSV, other tools, and more detail.\n\n"},"guides/glossary":{"title":"AddMaple Glossary","category":"Guides","slug":"guides/glossary","blurb":"Comprehensive glossary of key terms and concepts used throughout the AddMaple platform and documentation.","order":2,"filename":"glossary.md","uid":"guides/glossary","content":"\n# AddMaple Glossary\n\nThis glossary defines key terms and concepts used throughout the AddMaple platform and documentation.\n\n---\n\n## Core Platform Terms\n\n### **AddMaple**\nA browser-based data analysis platform that processes data locally without uploading to the cloud. Uses modern web APIs (File API, Worker API) to read and analyze files directly in your browser.\n\n### **Project**\nA workspace containing your dataset and all associated analyses, charts, dashboards, and reports.\n\n### **Dataset**\nThe raw data file you upload and analyze within AddMaple. Can be CSV, XLSX, SAV, JSON, Parquet, or AddMaple file formats.\n\n### **Column Store**\nAddMaple's proprietary data structure designed for fast pivoting, binning, and filtering of data within the browser.\n\n---\n\n## Data Types & Detection\n\n### **Multiple Choice (MC)**\nCategorical columns with a limited set of text results. Appears with turquoise bars on the chart dashboard. Used for single-answer survey questions or categorical data.\n\n### **Multiple Choice Plus (MC+)**\nColumns where there are multiple results per row. Appears with blue bars. Used for multi-select survey questions, tags, or any data where multiple values can be assigned to one record.\n\n### **Numeric**\nAutomatically detected numeric data (numbers, currency, percentages). Appears with green bars. AddMaple automatically creates bins/buckets for visualization in histograms.\n\n### **Opinion Scale**\nSpecial detection for opinion scales including both numeric scales (1-10) and text-based answers (Very Important, Somewhat Important, etc.). Allows display of Likert charts.\n\n### **Date/Datetime**\nAutomatically detected date and time columns. Enables time-based analysis and special date binning features.\n\n### **Text**\nFree text answers or responses. Future improvements will include full text search and automated tagging.\n\n### **Unique**\nColumns with different values for each row, typically identifiers. Cannot be filtered or pivoted but can be viewed in table or raw data view.\n\n### **Currency**\nAutomatically detected currency columns with currency symbols. Can be filtered and viewed like numeric columns.\n\n### **Percent**\nAutomatically detected percentage columns containing numbers followed by \"%\" signs.\n\n---\n\n## Data Processing & Preparation\n\n### **Binning**\nThe process of grouping numeric or date values into ranges for easier analysis and visualization.\n\n#### **Number Binning**\n- **Auto (Freedman-Diaconis rule)**: Statistically optimal bin width\n- **Equal Frequency**: Bins with similar counts\n- **Fixed Width**: Consistent interval bins\n- **Custom**: Manually defined ranges and labels\n\n#### **Date Binning**\n- **Auto**: Optimal time-based bins\n- **Calendar Periods**: Year, Quarter, Month, Week, Day, Hour\n- **Fixed Intervals**: Every X minutes/hours/days/weeks\n- **Custom Breakpoints**: User-defined date boundaries\n\n### **Weighting**\nApplying respondent weights to survey data for more accurate analysis. Adjusts results to better represent target populations when certain groups are over- or under-represented.\n\n### **Column Grouping**\nCombining similar columns with overlapping categories to analyze their totals together. Useful for aligning data across similar questions.\n\n### **Data Cleaning**\nProcess of preparing data for analysis, including merging categories, renaming columns, and handling missing values.\n\n---\n\n## Analysis & Visualization\n\n### **Pivot/Pivoting**\nThe process of cross-tabulating data by selecting two columns to analyze their relationship. Creates pivot charts and tables showing how one variable relates to another.\n\n### **Filter/Filtering**\nNarrowing down your dataset to focus on specific segments or values. Can be applied by clicking bars in charts, using the sentence builder, or from table views.\n\n### **Aggregation**\nSummarizing data using statistical measures:\n- **Total/Sum**: Adding up values\n- **Average/Mean**: Calculating the mean\n- **Median**: Finding the middle value\n- **Count Unique**: Counting distinct values\n\n### **Chart Dashboard**\nThe main interface showing all your data as interactive charts. Each column type appears with color-coded tiles (turquoise for MC, blue for MC+, green for numeric, etc.).\n\n### **Pivot Chart**\nInteractive charts created when you pivot two columns together. Show relationships between variables with statistical summaries.\n\n### **Likert Chart**\nSpecial chart type for opinion scale data, showing responses in a scale format. Created by pivoting opinion scale columns or grouping similar columns.\n\n### **Histogram**\nChart type for numeric data showing the distribution of values across bins or ranges.\n\n### **Horizontal Bar Chart**\nDefault chart type for categorical data, showing categories as horizontal bars with values.\n\n### **Box Plot**\nStatistical visualization showing quartiles, median, and outliers for numeric data.\n\n### **Scatter Plot**\nChart showing relationship between two numeric variables, often with regression lines.\n\n---\n\n## Statistical Analysis\n\n### **Chi-Square Test**\nStatistical test determining significant relationships between two categorical columns. Provides p-value, Cramér's V (relationship strength), and chi-square statistic.\n\n### **T-Test**\nStatistical test comparing means between two groups. Automatically performed when pivoting a numeric column with a categorical column having exactly 2 categories.\n\n### **Correlation**\nMeasures relationship strength between two numeric variables:\n- **Pearson Correlation**: For normally distributed data\n- **Spearman Correlation**: For non-normally distributed data\n\n### **Regression Analysis**\n- **Linear Regression**: Relationship between numeric variables\n- **Logistic Regression**: Relationship between numeric and binary variables\n- **Multivariate Regression**: Planned future feature\n\n### **ANOVA (Analysis of Variance)**\nStatistical test comparing means across multiple groups.\n\n### **Kruskal-Wallis Test**\nNon-parametric alternative to ANOVA for non-normally distributed data.\n\n### **P-Value**\nStatistical measure indicating the probability that observed relationships are due to chance. Lower values indicate stronger evidence of real relationships.\n\n### **Effect Size**\nMeasures the practical significance of statistical relationships:\n- **Cramér's V**: For categorical relationships (0-1 scale)\n- **Cohen's d**: For mean differences\n\n---\n\n## Dashboard & Reporting\n\n### **Dashboard**\nA collection of pages containing charts, text, images, and KPIs arranged for storytelling and sharing findings.\n\n### **Page**\nIndividual canvas within a dashboard containing various items. Tabs can be reordered by dragging.\n\n### **Item Types**\nComponents that can be added to dashboard pages:\n- **Text**: Written content\n- **Section**: Content dividers\n- **Call Out**: Highlighted information\n- **Image**: Visual content\n- **Video**: Video content\n- **Charts**: Saved analyses from My Collection\n\n### **My Collection/Insights**\nStorage area for saved charts and notes. Items can be organized into Collections and added to dashboards.\n\n### **Collections**\nFolders for organizing Insights by theme (e.g., \"Q3 Feedback\", \"Launch Readout\").\n\n### **Report**\nDocument containing selected charts and analyses for presentation or sharing.\n\n### **Publishing**\nMaking dashboards publicly accessible via shareable links. Can include password protection and explorable data options.\n\n### **Explorable Data**\nFeature allowing dashboard viewers to interact with underlying data by exploring selected columns.\n\n### **Public Link**\nShareable URL for published dashboards that can be accessed without AddMaple accounts.\n\n---\n\n## Text Analysis & AI Features\n\n### **AI Summary**\nAutomated analysis of text columns using AI to generate summaries of responses. Processing time varies by dataset size.\n\n### **Thematic Coding**\nProcess of categorizing text responses into themes or codes for analysis. Can be done manually or with AI assistance.\n\n### **AI Chart Explanation**\nAI-powered summaries explaining what current charts show and their key insights.\n\n### **Clean with AI**\nAutomated feature for cleaning, renaming, ordering, and merging categories in legends.\n\n### **Text Search**\nFeature for filtering text responses by specific words or phrases.\n\n---\n\n## User Interface Elements\n\n### **Sentence Builder**\nThe top black menu bar that displays applied filters and pivots in plain English. Interactive interface for adding filters, pivots, and aggregations.\n\n### **Legend**\nInterface for managing how categories appear in charts:\n- Rename categories\n- Reorder categories\n- Merge categories\n- Assign colors\n- Hide/show categories\n- Toggle between Ordered vs Independent categories\n\n### **More Menu**\nContext menu providing additional options for charts, columns, and analyses.\n\n### **Column Settings**\nInterface for configuring individual column properties including binning, types, and display options.\n\n### **Manage Columns**\nCentral interface for configuring all columns in a project, including types, binning, and other settings.\n\n### **Project Settings**\nConfiguration area for project-wide settings including color presets, weighting, and data management.\n\n---\n\n## Data Views\n\n### **Graph View**\nDefault view showing all columns as interactive charts on the chart dashboard.\n\n### **Table View**\nTabular display of data with options to add/remove columns, sort, filter, and explore individual rows.\n\n### **Row-by-Row View**\nIndividual record view showing complete responses with comparison to overall dataset. Useful for reading free-text responses and understanding context.\n\n### **Raw Data View**\nDirect display of original data without processing or formatting.\n\n---\n\n## Export & Sharing\n\n### **Export Formats**\n- **CSV**: Comma-separated values\n- **XLSX**: Excel format\n- **JSON**: JavaScript Object Notation\n- **Parquet**: Columnar storage format\n- **AddMaple Fast**: Optimized for fast loading\n- **AddMaple Compressed**: Smallest file size\n\n### **PowerPoint Export**\nExport charts and analyses to PowerPoint presentations.\n\n### **Excel Crosstabs**\nExport pivot tables to Excel format with proper formatting.\n\n### **Public Sharing**\nSharing dashboards and reports via public links with optional password protection.\n\n---\n\n## Technical Terms\n\n### **Browser-Based Processing**\nAll data analysis happens locally in your browser without uploading to cloud servers.\n\n### **File API**\nModern web API allowing browsers to read files directly from your computer.\n\n### **Worker API**\nWeb API enabling background processing for large datasets without blocking the user interface.\n\n### **Columnar Storage**\nData storage format optimized for analytical queries and fast aggregation.\n\n### **Effective Sample Size**\nAdjusted sample size accounting for weighting schemes in statistical calculations.\n\n### **Degrees of Freedom**\nNumber of values free to vary in statistical calculations.\n\n### **Expected Values**\nTheoretical counts expected if no relationship existed between variables (used in chi-square tests).\n\n### **Outlier Handling**\nStatistical methods for identifying and managing extreme values that might distort analysis.\n\n### **Welch-Satterthwaite Degrees of Freedom**\nMethod for calculating degrees of freedom in weighted t-tests.\n\n### **Kish Effective Sample Size**\nMethod for adjusting sample size calculations when using survey weights.\n\n---\n\n## Workflow Terms\n\n### **Save/Add to Dashboard**\nProcess of saving charts or analyses to My Collection for later use in dashboards.\n\n### **Swap Columns**\nFeature allowing you to switch which column is being pivoted vs. which is doing the pivoting.\n\n### **Related Columns**\nColumns that AddMaple suggests as potentially related based on data patterns.\n\n### **Cross-tabulation**\nStatistical table showing relationships between two categorical variables.\n\n### **Segmentation**\nProcess of dividing data into meaningful groups for analysis and comparison.\n\n### **Demographic Analysis**\nAnalysis focusing on population characteristics like age, gender, income, education, etc.\n\n### **Response Rate**\nPercentage of contacted individuals who completed a survey or provided data.\n\n### **Sample Size**\nNumber of observations or responses in your dataset.\n\n### **Confidence Level**\nStatistical measure of certainty in results (typically 95% or 99%).\n\n---\n\n*This glossary covers the main terms and concepts used throughout AddMaple. For detailed explanations and step-by-step instructions, refer to the specific user guide sections.*\n\n\n"},"guides/how-to-analyze-a-survey":{"title":"How to analyze a survey","category":"Guides","slug":"guides/how-to-analyze-a-survey","blurb":"Complete guide to analyzing survey data in AddMaple, from uploading your data to creating interactive charts, applying filters, and generating insights.","order":1,"filename":"how-to-analyze-a-survey.md","uid":"guides/how-to-analyze-a-survey","content":"# How to analyze a survey\n\nFirstly, here's a 🥳 for getting your survey out there and responded to. Now let's get it analyzed.\n\nWhen AddMaple reads your data file in your browser, it will automatically show you a graph summary page of ALL your data. That means all your columns will be analyzed and visualized as graphs in seconds. This happens automatically, you don't need to do anything other than give AddMaple read-only permission. The column order from your raw data from left to right, will be represented in the same order on the graph summary from top to bottom. \n\n \n\n**How to give AddMaple read-only permission:**\n\n- Click on New Project and select the raw data file you want to analyze. \n\n- Don't worry about cleaning the data or configuring it. AddMaple will do that for you.\n\n\nUse the top left \"VIEW DATASET AS\" menu to toggle between graphs, table and rows.\n\n \n\nRead on below for further details on how the graph, table and row-by-row pages work to help you analyze your data. \n\n\n**See all your data in graphs that you can interact with:**\n\nAddMaple automatically creates graphs from your data without you needing to clean the data or format it. This is done in seconds in your browser. \n\n**Watch the tutorial video below showing you how to do the following: **\n\n- Edit long column titles and column types [video timestamp 0:05 - 0:23]\n\n- Expand a graph to see it in full [0:23]\n\n- Filter by a bar in a graph. You must expand the graph first for this feature [0:28]\n\n- Pivot your data in 3 easy steps [0:40]. Read on to see the 3 steps broken down clearly. \n\n\n### An example pivot with step-by-step instructions\n\n- In this pivot example above we want to know how the different types of developers (full stack, front end, mobile etc) in our dataset learned to code. \n\n- This dataset contains 73,268 responses. \n\n- The column containing the type of developers is titled \"DevType\". This is the column we want to pivot which is why we expand it first. \n\n- The column containing the pivot criteria, how the developers learned to code is titled \"LearnCode\". \n\n- You can easily swap the pivot parameters with each other, thereby swapping which column pivots the data. Swap these by clicking on the existing pivoted columns in the black sentence bar, and select the first \"swap\" option. \n\nExpand the graph you would like to add pivots to. In our example this is the type of developer column, \"DevType\".\n\n\n\n\nUse the + icon to add a pivot to the expanded graph. You can add filters via the + icon too. \n\n\nSelect the column you would like to pivot your data by, which in our example is \"LearnCode\".\n\n\nVoila. Your pivot graph is produced. You can now add filters by hovering on segments you'd like to filter by. Or you could share your graph, or add it to your report as we explain below. \n\n\nYou can easily swap the pivot columns thus swapping the column being pivoted (sliced in segments) with the column applying the pivoting. Below we pivot the type of developer column with how they learned to code. And then we swap these two around, to look at how developers learned to code by the type of development work they do. \n\nThis is the pivoted graph we produced in our example. Next we want to swap the \"DevType\" and \"LearnCode\" columns. \n\n\nClick on either of the columns in the black box. Then click on the first option in the drop down menu which reads, \"Swap with ...\". That's all you need to do. Done. \n\n\nYou're now looking at the LearnCode column pivoted by DevType. \n\n\nAdd interactive graphs to your report using the More menu at the top right of the black box. \n\n\n**Our tables aren't just static presentations of your data. They are interactive. **\nAddMaple turns any raw file into a table. But unlike Excel, we don't include all columns and overwhelm you with information. We allow you to select and deselect which columns you need in your table. \n\n**Watch the tutorial video below showing you how to do the following: **\n\n- Add columns [timestamp 0:04 - 0:12]. Select columns to add to your table by clicking on them. \n\n- Sort columns [0:15]. Use the sort icon. \n\n- Remove columns [0:17]. Simply click on any selected columns, to remove them from your table. Selected columns have a tick beside them. \n\n- Segment your data [0:23]. Add Filters to your table using the top + icon in the top menu. \n\n- Expand individual records [0:52] . If you see an interesting response in the table and want to read that record in full, click on the corresponding record number on the left. This brings up that record's row-by-row view where you can read free-text responses too. Here you can also see how that respondent's answers or that data record, compares to the overall data cohort you're looking at. Return to the table/graph view via the top left \"View DataSet As menu\".\n\n\n**Filter data by clicking on a response in your table**\n\n- Being able to filter by responses in a table is more intuitive. \n\n- In the example video we click on \"Master's degree\" in the \"EdLevel\" column to add \"Master's degree\" as a filter. We then only see responses where candidates selected that option in their response. \n\n- Then we add \"Hybrid\" from the \"RemoteWork\" column as a filter. \n\n- You can specify whether you want to include or exclude the filtered results from your table. If you choose to exclude the filtered results, you won't see responses containing the filters you applied. The default is to include the applied filters as you see from the video. \n\n\nColumns containing quantitive data (multiple choice questions, opinion scales etc) are automatically color-coded. This helps you spot matching responses.\n\n**Reading individual records can help you understand the context of that specific record. **\nHowever, we show you how that record compares with the overall cohort, so that you can easily spot outliers. A deep dive with a helping of big picture perspective. This applies to survey data and other quantitive data. The free-text filters you can apply is probably one of the most useful aspects of the row-by-row view. This way you can only read records containing certain words to save time. \n\n\n**Watch the tutorial video below showing you how to do the following: **\n\n- See how an individual record compares with the overall cohort you're looking at [0:08]\n\n- Add filters by clicking on a response in that record [0.28]. In the tutorial example, we filter by developers who learned to code using \"Other online resources (e.g. videos, blogs, forums)\" by clicking on that response. \n\n- Switch between viewing individual records, graphs, table and report [0:36]\n\n- Read free text responses and apply word filters [0:43]. This enables you only to read records including/excluding specific words\n\n\n\nWe learn so much from survey data, both when we look at the responses as a whole, and when we apply filters to look at how specific segments answer questions, in order to compare their responses with other segments. This is often where deeper insights hide from plain sight. From demographics to user preferences, opinions, work history and more, our filters are easy to apply and remove. We even allow you to segment your data by specific words a respondent included in their free text response if you included open-ended questions!\n\nYou could also add filters using the information provided by your survey tool, e.g. Survey Monkey. Data such as survey completion times (perhaps filter out possible rushed responses), or IP regions, completion time stamps (find the night owls) or even devices used to complete the survey (find those who do *everything* on their phone) and so on. Needless to say, the reasons *Why it is useful to segment your data* are so numerous, they deserve a dedicated article.\n\n***Right, here's how to apply filters to your data***\n\n \n\n##### **Method 1: Filter by the top \"+\" button. Watch the video tutorial below.**\n\n**This top black menu box serves as a sentence builder where the applied filters and pivots are written in plain english.*\n\n1. Tap the \"+\" icon\n\n1. Select \"Add Filter\"\n\n1. Select the column that you want to filter the data from\n\n1. Select whether to include or exclude the values you will apply next. You could remove a segment from the dataset or you could only view the data where those values are applied.\n\n1. The video tutorial below shows you how to segment your dataset by respondents who learned to code using online courses. With the filter applied, you can view every column graph automatically update with this applied segmentation filter.\n\nThis video tutorial shows you how to filter data using the \"+\" button found on the top menu\n\n\n##### **Method 2: Filter data directly from a bar in a chart**\n\n \n\nThis method allows you to filter by the interesting metrics you see on a graph. Rather than decide up front what you want to filter by, this method allows you to filter by the interesting insights you see in the graphs themselves.\n\n1. Expand a graph you want to explore further.\n\n1. Hover over a bar in the graph (not the empty space) that you want to filter your data by. When you do this you will notice the following text appear, \"filter data by this value\" which you should click on.\n\n1. That's it.\n\n1. Note, that filtering a single-response Multiple Choice question (the teal MC questions) work slightly differently to the multiple-response Multiple Choice questions (the blue MC+ questions). \n**Single-response question filtering**: Segment by one value **OR** other values. \n**Multiple- response question filtering:** Segment by one value **AND** other options. \n\n### Clicking on a response to add a filter can also be done when you're in the table and individual row-by-row views. \n\n\n\nThis video tutorial shows you how to filter data directly from a bar in a graph\n\n"},"guides/instant-automatic-analysis":{"title":"How AddMaple speeds up Analysis with Automation","category":"Guides","slug":"guides/instant-automatic-analysis","blurb":null,"order":4,"filename":"instant-automatic-analysis.md","uid":"guides/instant-automatic-analysis","content":"# How AddMaple speeds up Analysis with Automation\n\n### From detecting data types, to automatic numeric binning, we explain how automation makes AddMaple fast and breezy to use\n\n### Why and how we automate the data cleaning and preparation \n\nYou've probably seen that AddMaple summarizes your data files in less than five seconds, giving you tables and charts for each column. If you're wondering how this is possible, we'll try break down some of the main automation tasks we carry out for you. Ultimately we believe that the more time, energy and curiosity you save during the initial data prep, the more reserves you'll have left for interpreting the data, writing your report and communicating your insights. Hence why we prioritize automating this part of your workflow, so you don't even know what happened! \n\nLike Sherlock, we're detectives looking for clues in your data so that we know with a high degree of confidence what type of data each column contains. This is done programmatically and is quite involved, visit this page for a list of data types we [detect](../frequently-asked-questions/which-column-types-are-detected). \n\nIn short, we automatically or *automagically* detect:\n\n**Numeric data** such as salaries, ages, product quantities sold and so on. With numeric data identified, we determine the highest and lowest values (maximum and minimum) and help you create bins or buckets with an even spread of data. This is why you would see a histogram waiting for you on the dashboard. These columns are labeled as NUM and are green. We also detect **Currencies **and** Percentages **- they show up with specific icons in our interface but you interact with them in the same way as our numeric columns. \n\n \n\n**Categorical data **such as answers to a multiple choice question. We detect when columns only contain one tag, for example, the column titled 'Country of Birth', would only contain one country for each record in the column as a tag. We also detect when a column contains multiple tags in one column, for example, responses to the question, 'Select all supermarkets you visited last month' would contain more than one supermarket, with each record having a different combination of supermarket tags. For these tricky columns, we give you a count of all the supermarkets, so you can see how many times each supermarket was selected. We also allow you to filter by one or more supermarkets, to see all related supermarkets for the ones selected. \n\nHow can you tell if a categorical column in your dataset contains one tag per record or multiple? We help you differentiate between these categorical columns with colors. Single tag columns are turquoise and are labeled as MC for Multiple Choice. Note this is applicable outside surveys, this is used for any dataset containing one tag. Multi-tag columns are blue and are titled Multi-Select, and they tell you that there are two or more tags per record in that column. \n\n\n**Dates** and timestamp such as review date and time. We detect dates and time in a wide range of formats to support the most commonly used structures. This is useful for error logs, events captured by your servers, the dates and times a respondent submitted a survey and so on. \n\n \n\n**Duration** columns such as how long a user interacted with a feature. We detect this column type as a type of numeric value, where records are binned into duration ranges according to the max/min duration values in that column. If you have duration data, you'll be able to see how many records fall within the same duration range so you can see how many records fall within each duration bucket for easy analysis. You'll then be able to filter down by a range to understand more about those who did something for a longer or shorter time period for example. \n\n**Messy data** such as **Empties **within a column**, N/A** within a category/ numeric columns and even mid-dots aka interpuncts ( · ) some people love to insert in response to open-ended questions. We detect these and more, and group them off for you, for smooth onward analysis, so that you don't have to first 'clean' columns containing these irregularities. Many data analysis tools require you to remove N/A records within numeric columns for example, we handle this for you. Regarding missing data, you would usually need to replace these records with placeholder text such as 999 or BLANK, etc but there is no need to do this in AddMaple because we automatically detect and group off data like this for you. If text columns contain some records with a single mid-dot, we group them off with the empty records so that you can proceed to analyze the text. \n\n\n**Opinion scales **or Likert scales show up in pink. We detect both text and numeric variants, for example you may have categories such as \"Strongly Agree, Agree, egc.\" or just numbers between 1 and 7. AddMaple creates special Likert charts for this type of data and groups together related columns right from the dashboard.\n\n \n\n**Text** columns show up in green and area ready for you to explore with interactive word clouds. We also support AI powered thematic analysis allowing you to convert your open-ends into quantifiable and explorable data. \n\n \n\nAll of this detections happens instantly, even on large datasets.\n\n### Tag Detection\n\nDealing with tags or survey questions that can have multiple responses to the same question is difficult to do in spreadsheets. \n\nThis is where AddMaple shines. We automatically detect this data type whether the data is separated by commas (,), semicolons (;), colons (:), or pipes (|). In a spreadsheet a common approach of dealing with this data would be to separate it using formulas into multiple columns - but that makes filtering and pivoting much harder. \n\nIn AddMaple the data stays in the same column and you can easily explore, filter and pivot.\n\nAfter a data set has been loaded and the data types automatically detected, AddMaple produces instant summaries of each column. This enables you to see an overview of your data at a glance.\n\nBecause the column types are automatically detected, we can display different summaries for each data type. \n\n \n\n\n\n\nAddMaple performs intelligent bucketing (binning or grouping) of numeric data.\n\nOur algorithm handles large, small and negative numeric ranges. The buckets that we create are rounded to sensible values and are not distorted by outliers.\n\nAs filters are applied the buckets are recalculated in an instant making it easy to dive into a particular range.\n\nThe below data was imported as raw numeric values, but AddMaple automatically grouped it into ranges.\n\n\nAddMaple automatically performs the appropriate [statistical tests](https://addmaple.com/features/key-drivers-and-statistical-relationships) for you as you explore your data. \n\nWhen you expand a column, we compare that column against all others in your dataset to find those that have significant relationships. This features saves a lot of time and helps you uncover hidden insights in your data.\n"},"guides/statisticalcalculations":{"title":"Statistical Calculations","category":"Guides","slug":"guides/statisticalcalculations","blurb":null,"order":5,"filename":"statisticalcalculations.md","uid":"guides/statisticalcalculations","content":"# Statistical Calculations\n\n### Find out how to use AddMaple's stats engine and how it works\n\n\n\nWe recently launched our new statistics engine, designed to make data analysis both accessible and efficient. This engine automatically performs the appropriate statistical tests on your data - reducing the time it takes to go from dataset to useful insights.\n\nFor data experts, the new engine accelerates your workflow by handling the statistical tests, letting you spend more time interpreting results and making decisions. For those less familiar with statistics, it eliminates the complexity and jargon, providing straightforward insights without requiring in-depth statistical knowledge.\n\nIn this article, we'll explore how the new engine works, the types of statistical tests it uses, and the practical benefits it offers for your data analysis needs.\n\n\n\nThe new statistics engine in AddMaple is designed to automatically handle a variety of statistical tests, streamlining your data analysis process.\n\nThe engine first examines your dataset to determine the types of data in each column. Based on this analysis, it selects the appropriate statistical tests to compare columns, ensuring that the results are both relevant and accurate. Here are the types of tests the engine uses:\n\n**Chi-Square Test**: Used when both columns contain categorical data. This test helps determine if there is a significant association between the categories of the two variables.\n\n> Example: Imagine you conducted a survey to see if there is a relationship between people's preferred type of exercise (running, swimming, cycling) and their age group (under 30, 30-50, over 50). The Chi-Square test can help you determine if the preference for exercise type is related to the age group of respondents.\n\n**ANOVA (Analysis of Variance)**: Applied when comparing one categorical column and one numerical column. It helps identify whether there are any statistically significant differences between the means of different groups.\n\n> Example: Consider a medical study that looks at the effect of different diets (low-carb, low-fat, Mediterranean) on blood pressure levels. ANOVA can be used to determine if there are significant differences in blood pressure changes among the different diet groups.\n\n**Kruskal-Wallis Test**: Applied when comparing one categorical column and one numerical or ordinal column, especially useful in scenarios where some categories may have small sample sizes and the data do not assume a normal distribution. It assesses whether there are statistically significant differences between the distributions of different groups.\n\n**> **Example: Consider an ecological study assessing the impact of various conservation strategies (community management, protected areas, none) on the diversity of species in small, isolated patches of habitat. Given the small sample sizes from some habitat patches, the Kruskal-Wallis test is suitable for determining if there are significant differences in species diversity distributions among the conservation strategy groups.\n\n**T-Test:** Used when comparing one categorical column with only two categories against a numerical column. This test checks if there are significant differences between the two groups.\n\n> Example: Suppose you want to compare the test scores of students who studied using two different methods: traditional learning vs. online learning. The T-Test can help determine if there is a significant difference in the test scores between these two groups.\n\n**Correlation Tests (Pearson's and Spearman's):** Used when both columns contain numerical data. Pearson's correlation is applied if the data is normally distributed, while Spearman's correlation is used if the data is not normally distributed. These tests measure the strength and direction of the relationship between the two numerical variables.\n\n> Example: Imagine you are analyzing data to see if there is a relationship between hours of exercise per week and cholesterol levels. The Pearson's or Spearman's correlation tests can help determine if there is a significant correlation between these two numerical columns.\n\n\nBy automating these tests, the new statistics engine saves you time and effort, allowing you to focus on interpreting the results rather than worrying about the technical details of statistical analysis. AddMaple automatically highlights the columns most related to the column you are viewing, surfacing hidden insights and patterns that might otherwise be overlooked. This not only streamlines your workflow but also ensures that you don't miss any significant relationships in your data. \n\nOur statistics engine is designed to choose the appropriate statistical test for each pair of columns in your dataset, ensuring accurate and relevant results. This optimized algorithm runs very fast, even on large data sets, and performs all relevant tests automatically.\n\nHere is a breakdown of how we perform each statistical test:\n\n### **Chi-Square Test**\n\nFor pairs of columns containing categorical data, the engine performs a Chi-Square test. Here's how it works:\n\n**Calculate Expected Frequencies**: \n\nThe engine calculates the expected frequencies for each category combination based on the marginal totals.\n\n**Compute Chi-Square Statistic**: It then compares the observed frequencies with the expected frequencies to compute the Chi-Square statistic using the formula - \n\n*\\[\n \\chi^2 = \\sum \\frac{(O_i - E_i)^2}{E_i} \n\\]*\n\nWhere *\\(O_i\\)* is the observed frequency for each category combination and* \\(E_i\\)* is the expected frequency.\n\n**Determine P-Value**: The Chi-Square statistic is compared against the Chi-Square distribution with the appropriate degrees of freedom to determine the p-value, indicating the significance of the association between the categories.\n\n**Calculate Cramer's V**: To measure the strength of the association between the categories, the engine calculates Cramer's V. Here's how it works:\n\n**Chi-Square Value**: Use the computed Chi-Square statistic.\n\n**Sample Size**: Determine the total number of observations.\n\n**Minimum Dimension (k)**: Find the smaller of (number of rows - 1) and (number of columns - 1).\n\n**Cramer's V Formula**: \n\n*\\[ V = \\sqrt{\\frac{\\chi^2}{n \\times k}} \\]*\n\nWhere *\\(\\chi^2\\)* is the Chi-Square statistic, *\\(n\\) *is the total number of observations, and *\\(k\\)* is the minimum dimension.\n\nBy including Cramer's V, the engine not only tells you whether there is a significant association but also how strong that association is, providing a more comprehensive understanding of the relationship between your categorical variables.\n\n### **ANOVA (Analysis of Variance)**\n\nFor comparing one categorical variable and one numerical variable, the engine uses ANOVA. Here's the process:\n\n**Calculate Group Means**: The engine calculates the mean of the numerical variable for each category.\n\n**Compute Variance**: It then computes the variance within groups and between groups.\n\n**Calculate F-Statistic**: The ratio of between-group variance to within-group variance is calculated to obtain the F-statistic.\n\n**Determine P-Value**: The F-statistic is compared against the F-distribution to determine the p-value, which indicates whether there are significant differences between group means.\n\n**Calculate Eta Squared *\\(\\eta^2\\)***: To measure the effect size, the engine calculates eta squared. Here's how it works: \n\n**Sum of Squares Between (SSB)**: The sum of squared deviations of each group mean from the overall mean, multiplied by the number of observations in each group.\n\n**Sum of Squares Total (SST)**: The sum of squared deviations of each observation from the overall mean. \n\n**Eta Squared Formula**: \n\n*\\[ \\eta^2 = \\frac{\\text{SSB}}{\\text{SST}} \\]*\n\nWhere *\\(\\eta^2\\)* is the proportion of total variance attributable to the factor. \n\nBy including eta squared, the engine not only tells you whether there are significant differences between groups but also quantifies the magnitude of the differences, providing a more comprehensive understanding of the relationship between your categorical and numerical variables.\n\n### **Kruskal-Wallis Test**\n\nFor comparing one categorical variable with one numerical or ordinal variable where there are small sample sizes in some categories, the engine uses the Kruskal-Wallis test. Here's the process:\n\n1. **Calculate Group Ranks**: The engine assigns ranks to all observations across the groups and calculates the sum of ranks for each group.\n\n1. **Compute Test Statistic**: It computes the H statistic, which involves the following steps:\n\n1. Calculate the sum of squared ranks for each group, adjusted by the number of observations in each group. Sum these values across all groups and adjust for the total number of observations to derive the H statistic.\n\n1. **Determine P-Value**: The H statistic is compared against the chi-squared distribution to determine the p-value, which indicates whether there are significant differences between group distributions.\n\n1. **Calculate Eta Squared *\\(\\eta^2\\)***: To measure the effect size, the engine calculates eta squared. This allows us to order related columns by the effect size as well as the p-value.\n\n### **T-Test**\n\nFor comparing one categorical variable with two categories against a numerical variable, the engine performs a two-sided T-Test:\n\n- **Calculate Group Means and Variances**: The engine computes the means and standard deviations of the numerical variable for the two categories.\n\n- **Compute T-Statistic**: The difference between the means is divided by the standard error of the difference to obtain the T-statistic.\n\n- **Determine Degrees of Freedom**: The degrees of freedom (dof) are calculated based on the sample sizes of the two groups.\n\n- **Compute P-Value**: The T-statistic is compared against the T-distribution to find the p-value, indicating if there is a significant difference between the two groups.\n\n### **Correlation Tests** (Pearson's and Spearman's)\n\nFor pairs of numerical columns, the engine uses two-sided correlation tests:\n\n**Pearson's Correlation**: Used if the data is normally distributed.\n\n- Check Normality: The engine checks if both arrays of data are normally distributed.\n\n- Compute Pearson's Correlation Coefficient: It calculates the correlation coefficient, which measures the strength and direction of the linear relationship.\n\n**Spearman's Correlation**: Used if the data is not normally distributed.\n\n- Rank the Data: The engine ranks the data for both variables.\n\n- Compute Spearman's Rank Correlation Coefficient: It calculates the correlation coefficient based on these ranks.\n\nFor both correlation tests:\n\n- 3. Calculate T-Score: The correlation coefficient is used to calculate the t-score, which involves the sample size.\n\n- Determine Degrees of Freedom: The degrees of freedom (dof) is calculated as the sample size minus 2.\n\n- Compute P-Value: The t-score and degrees of freedom are used to determine the p-value, indicating the significance of the correlation.\n\nBy performing these tests automatically and highlighting the most relevant columns, AddMaple's statistics engine surfaces hidden insights and saves you time.\n\n \n\n \n\nAt AddMaple we want to make these powerful statistical techniques easy to use and explore. Rather than ask you to choose a complex set of options, we choose the most appropriate tests, run them automatically and present the results to you in an intuitive manner.\n\nPlease see examples below of the different ways in which we present these results back to you.\n\n### Related Columns\n\nWhen you expand on any column in AddMaple, we run all the calculations as described above. The results are show in the stats tab. In the image below we can see that AddMaple has found a moderate relationship between \"Age Category\" and \"Device Used\".\n\n\n\n \n\n### Relationship Highlight\n\nWhen clicking on a related column, AddMaple will take you to a pivot chart with the relationship highlight. For example in the image below we can see Age Category vs Device Used, with a clear preference for Tablets among the 65+ age category. AddMaple provides a highlight sentence about the relationship - in this case it is a moderate relationship. \n\n\n\n \n\n### Relationship Overview\n\nBy clicking on the \"See more\" link or on the \"Stats\" tab, AddMaple will give you more details on the relationship. We give a series of dynamic paragraphs depending on the columns chosen, the statistical test that was run, and the results of that test. In the example below you can see an explanation of how the Chi-Square results for \"Age\" vs \"Device Used\".\n\n\n\n \n\n### The numbers behind the overview\n\nBelow the overview we provide the underlying numbers from the stats tests performed. If you hover the name of each item we give a clear description of what the number is and how it was calculated.\n\n\n\n \n\n### Further Insights\n\nWhere applicable we run additional tests between categories. In the below example you can see that while there is a moderate relationship overall between \"Age Category\" and \"Device Used\", there is a strong relationship when comparing Smartphone users vs Laptop and Tablet users. This analysis helps you dive deeper to understand the particular categories that are having the biggest impact on the relationship. \n\n\n\n \n\n### Visual Exploration on the Chart Dashboard\n\nWhen you've pivoted by a single column, you are able to go back to the chart dashboard and view all other columns pivoted by that column. The columns are ordered by the strength of the relationship. This allows you to quickly explore visually the impact of one column on all other columns in your dataset. Below we can see the two columns with the strongest relationship to \"Age Category\". \n\n\n\n \n\nFor further details on how to run each type of test please see these guides:\n\n1. [How to run a T-Test](../stats/ttest)\n\n1. [Correlation Tests (Pearson's and Spearman's)](../stats/correlation)\n\n1. [How to run an ANOVA test](../stats/anovatest)\n\n1. [How to run a Chi-Square Test](../stats/chi-square)\n\n1. [Exploring Related Columns](../stats/related-columns)\n\n \n\n \n\nAddMaple's new statistics engine is designed to make your data analysis process more efficient and insightful. By automatically selecting and performing the appropriate statistical tests, it saves you time and reduces the complexity of your workflow. Whether you are an experienced analyst or new to data statistical tests, AddMaple helps you quickly uncover significant relationships and hidden insights in your data. With the ability to highlight the most relevant columns and provide clear visualizations, AddMaple ensures that you can focus on getting useful insights from your data in as short a time as possible.\n\nWe are a small team passionate about making data analysis fast, intuitive and fun. We are continually improving this feature, if there is something you'd like to see, then please let us know. We hope this module helps you uncover hidden insights in your data.\n\nThe AddMaple Team\n\n \n\n "},"insights/add-to-dashboard":{"title":"Use Insights in Dashboards","category":"Insights","slug":"insights/add-to-dashboard","blurb":"Pin Insights to dashboards to support your narrative.","order":6,"filename":"add-to-dashboard.md","uid":"insights/add-to-dashboard","content":"\n## Add an Insight to a dashboard\n\n1. Open **My Collection** (Actions → Add to Dashboard → My Collection)\n2. Select one or more items; optional tag filter at top-right\n3. Click **Add to Dashboard**; items are added to the current page\n4. Chart items keep their settings; some charts also add an AI explanation block\n\n\n\n---\n\n## Link back to analysis\n\nWhen available, the added item keeps a link to its source chart or view for quick reference.\n\n\n"},"insights/collection-guide":{"title":"Using My Collection","category":"Insights","slug":"insights/collection-guide","blurb":"Select, tag, export, and add items to dashboards from My Collection.","order":5,"filename":"collection-guide.md","uid":"insights/collection-guide","content":"\n## Select items\n\n- Click an item to toggle selection; preview thumbnails show when available\n- The actions bar appears at the bottom when items are selected\n\n## Actions bar\n\n- **Add to Dashboard**: Pick a dashboard and page, or create a new dashboard/page on the fly. Chart items may also add an AI explanation block when available.\n- **Assign Tags**: Bulk add/remove tags. Use tag filters to narrow the list.\n- **Download as PowerPoint**: Exports selected charts/tables.\n- **Delete**: Bulk delete selected items with confirmation.\n\n\n\n## Add to dashboards (from a dashboard)\n\n- In a dashboard, choose **Actions → My Collection**, select items (with optional tag filter), then click **Add to Dashboard** to place them on the current page.\n\n## Shortcuts and constraints\n\n- Press Enter to confirm names when creating a dashboard or page from the selector\n- PowerPoint export supports charts/tables only\n- Chart IDs are uniquified when adding from Collection to avoid conflicts in dashboards\n\n\n"},"insights/collections":{"title":"Manage Collections","category":"Insights","slug":"insights/collections","blurb":"Create, rename, move, and delete Collections to organise your Insights.","order":4,"filename":"collections.md","uid":"insights/collections","content":"\n## Create and rename\n\n1. Open Insights\n2. Click **New Collection**\n3. Name it and press Enter\n4. Rename anytime from the context menu\n\n\n\n---\n\n## Filter and select\n\n- Filter by tags in the modal's header\n- Click items to select; the footer shows count selected\n\n---\n\n## Add to Dashboard\n\n- Click **Add to Dashboard** to add the selected items to the current dashboard/page; chart items may also add an AI explanation block when available\n\n\n"},"insights/create":{"title":"Create an Insight","category":"Insights","slug":"insights/create","blurb":"Capture a finding with text, charts, and links.","order":3,"filename":"create.md","uid":"insights/create","content":"\n## Create a new Insight\n\nYou create Insights while analyzing data or from selection menus.\n\n1. Use save menus to store a chart to **My Collection**\n2. (Optional) Add tags; items appear in the Collection modal with filters\n3. Edit later from the Collection list\n\n\n\n---\n\n## Edit an Insight\n\n- Click an Insight to open it\n- Update text, replace attachments, or add links\n- Changes save automatically or via **Save**\n\n\n"},"insights/insights-overview":{"title":"Insights Overview","category":"Insights","slug":"insights/insights-overview","blurb":"Learn the Insights tabs and how to move content into dashboards.","order":1,"filename":"insights-overview.md","uid":"insights/insights-overview","content":"\n## Tabs\n\n- **My Collection**: Saved items with tags and bulk actions\n- **Dashboards & Report**: Manage dashboards and see publish status\n- **Shared Charts**: Project charts available to reuse\n- **AI Operations**: Summaries, explanations, and codes\n\n\n\n## Typical flow\n\n1. Save charts to **My Collection** (or capture results in AI Operations)\n2. Use **Add to Dashboard** to assemble a story\n3. Open the dashboard to arrange, style, and publish\n\nSee also: Using My Collection.\n\n\n"},"insights/overview":{"title":"Insights & Collections","category":"Insights","slug":"insights/overview","blurb":"Capture findings as Insights and organise them into Collections.","order":2,"filename":"overview.md","uid":"insights/overview","content":"\n## What are Insights?\n\nInsights (My Collection) store charts and notes you've saved. From there you can add selected items to any [dashboard](../dashboard/overview).\n\n\n\n---\n\n## Collections\n\nCollections are folders for your Insights. Use them to group related ideas (e.g. \"Q3 Feedback\", \"Launch Readout\"). Learn more about [creating collections](../insights/create).\n\n- Create multiple Collections\n- Move Insights between Collections\n- Rename or delete Collections anytime\n\n\n"},"insights/share-export":{"title":"Share & Export Insights","category":"Insights","slug":"insights/share-export","blurb":"Share Insights with your team or export to documents.","order":7,"filename":"share-export.md","uid":"insights/share-export","content":"\n## Share\n\n- Insights are primarily used to assemble dashboards; share via published dashboards\n\n\n\n---\n\n## Export\n\n- Copy content to external docs\n- Publish your dashboard and export via the dashboard export options\n- From the Selection menu, use **Download as PowerPoint** to export selected charts/tables\n\n\n"},"integrations/athena":{"title":"Athena","category":"Integrations","slug":"integrations/athena","blurb":"Connect AddMaple to AWS Athena in a team workspace and analyze query results as a project.","order":7,"filename":"athena.md","uid":"integrations/athena","content":"# Athena\n\nThe Athena integration lets your team create AddMaple projects from SQL queries, without exporting files first.\n\nThis integration is intended for **team/enterprise** workspaces.\n\n## Before you start\n\nYou’ll need:\n\n- An AWS **Access key ID** and **Secret access key**\n- The AWS **Region** where Athena runs\n- An Athena **Database** and **Workgroup**\n- An S3 **Output bucket** where Athena query results are written\n\nFor best security, use IAM credentials with the minimum permissions needed to run queries and read results.\n\n## How to connect\n\n### 1. Open your team admin page\n\nIn AddMaple, open your team admin area and scroll to the **Connections** section.\n\n### 2. Add a new connection\n\nClick **Add New Connection**.\n\n### 3. Choose \"Athena\"\n\nSet **Connection Type** to **Athena**.\n\n### 4. Fill in the connection details\n\nEnter:\n\n- **Name**: a friendly name for your connection\n- **Region**\n- **Access key ID**\n- **Secret access key**\n- **Database**\n- **Workgroup**\n- **Output bucket**\n\nClick **Add Connection**.\n\n## Test the connection and create a project\n\n1. In the connections list, click **Test** on your Athena connection.\n2. AddMaple will show a list of **databases and tables**.\n3. Click **Select** on a table to generate a starter query (or write your own SQL in **SQL Query**).\n4. Click **Test Project** to preview sample rows.\n5. Click **Create Project** to turn the query into an AddMaple project.\n\n## Further reading\n\n- [Integrations](/help/integrations/overview)\n"},"integrations/google-drive":{"title":"Google Drive","category":"Integrations","slug":"integrations/google-drive","blurb":"Import a file directly from Google Drive and start analyzing in AddMaple.","order":5,"filename":"google-drive.md","uid":"integrations/google-drive","content":"# Google Drive\n\nUse the Google Drive integration to start a project from a file stored in Drive, without downloading it to your computer first.\n\n## How to connect\n\n### 1. Start a new project\n\nSign in to AddMaple and open the **New Project** page.\n\n### 2. Click \"Google Drive\" in the cloud services section\n\nUnder **Connect cloud service**, click **Google Drive**.\n\n### 3. Authorize access (first time only)\n\nIf prompted, choose the Google account that has the file and authorize AddMaple to access Drive so it can open the file picker.\n\n### 4. Pick a file\n\nSelect the file you want to analyze (for example a CSV or Excel file). AddMaple will import it and create a project automatically.\n\n### 5. Start analyzing\n\nOnce the import finishes, AddMaple will open your new project and automatically:\n\n- Detect column types (text, numbers, categories, dates)\n- Generate readable column names\n- Create initial charts and summaries\n\n## Re-authorizing Google Drive\n\nIf your Google Drive access token expires, AddMaple will show a message asking you to re-authorize. Click **Re-authorize Google Drive** and follow the prompt, then the project will reload.\n\n## Further reading\n\n- [Integrations](/help/integrations/overview)\n- [Importing and Preparing Data](/help/preparation/importing-and-preparing-data)\n"},"integrations/overview":{"title":"Integrations","category":"Integrations","slug":"integrations/overview","blurb":"Connect AddMaple to survey platforms, cloud storage, and enterprise data sources.","order":1,"filename":"overview.md","uid":"integrations/overview","content":"## Integrations\n\nIntegrations let you start a project without manually downloading and uploading files. You can connect AddMaple to survey platforms, select a dataset, and begin analyzing immediately.\n\n---\n\n## Available integrations\n\n- **Typeform**: Sign in to Typeform, choose a form, and analyze responses in AddMaple. See [Typeform](/help/integrations/typeform).\n- **SurveyMonkey**: Sign in to SurveyMonkey, choose a survey, and analyze responses in AddMaple. See [SurveyMonkey](/help/integrations/surveymonkey).\n- **Tally**: Paste a Tally API key, choose a form, and analyze submissions in AddMaple. See [Tally](/help/integrations/tally).\n- **Google Drive**: Pick a file from Google Drive and import it into AddMaple. See [Google Drive](/help/integrations/google-drive).\n- **Athena**: For teams: connect AWS Athena and create projects from SQL queries. See [Athena](/help/integrations/athena).\n\n---\n\n## If you already have a file\n\nIf you’ve already downloaded a CSV/Excel/SPSS file, you can upload it from the **New Project** page instead. See [Importing and Preparing Data](/help/preparation/importing-and-preparing-data).\n"},"integrations/surveymonkey":{"title":"SurveyMonkey","category":"Integrations","slug":"integrations/surveymonkey","blurb":"Connect your SurveyMonkey account to AddMaple and analyze your survey responses directly without downloading files.","order":3,"filename":"surveymonkey.md","uid":"integrations/surveymonkey","content":"# SurveyMonkey\n\nAddMaple integrates directly with SurveyMonkey, allowing you to analyze your survey responses without needing to download and upload files. Your responses sync automatically each time you open your project.\n\n## How to connect\n\n### 1. Start a new project\n\nSign in to AddMaple and go to the **New Project** page.\n\n### 2. Click \"Survey Monkey\" in the cloud services section\n\nUnder **Connect cloud service**, click the **Survey Monkey** option.\n\n\n\n### 3. Authorize AddMaple\n\nYou'll be redirected to SurveyMonkey to authorize AddMaple to access your surveys and responses. Click **Authorize** to grant access.\n\nAddMaple requests read-only access to:\n\n- Your surveys (to show you a list to choose from)\n- Your responses (to analyze the data)\n\n### 4. Select a survey\n\nAfter authorization, you'll see a list of all your SurveyMonkey surveys. Click on the survey you want to analyze.\n\n### 5. Start analyzing\n\nAddMaple will fetch your responses and automatically:\n\n- Detect column types (text, numbers, categories, dates)\n- Merge multi-select questions into single columns\n- Generate readable column names\n- Create initial charts and summaries\n\n## Keeping data in sync\n\nEach time you open your SurveyMonkey project in AddMaple, it fetches the latest responses. There's no need to manually refresh or re-upload data.\n\n## Reconnecting\n\nIf your SurveyMonkey authorization expires, AddMaple will prompt you to re-authorize. Simply click the **Re-authorize** button and follow the same authorization flow.\n\n## Supported question types\n\nAddMaple handles all SurveyMonkey question types:\n\n| SurveyMonkey Type | AddMaple Type |\n|-------------------|---------------|\n| Single Textbox, Comment Box | Text |\n| Multiple Choice (single answer) | Category |\n| Multiple Choice (multiple answers), Checkboxes | Multi-Select |\n| Rating Scale, Matrix/Rating Scale | Numeric |\n| Dropdown | Category |\n| Date/Time | Date |\n| Matrix (single answer per row) | Expanded to individual columns |\n\n## Privacy\n\nYour SurveyMonkey data is processed in your browser. AddMaple stores only the connection credentials needed to fetch your data—your actual survey responses are never stored on our servers.\n\n## Troubleshooting\n\n### \"Access Denied\" error\n\nMake sure your SurveyMonkey account has API access enabled. Some SurveyMonkey plans may restrict API access.\n\n### Missing surveys\n\nOnly surveys you own or have been shared with you will appear in the list. Check your SurveyMonkey account permissions.\n\n## Further reading\n\n- [Integrations](/help/integrations/overview)\n- [How Do I Upload My Survey Data Into AddMaple](/help/frequently-asked-questions/how-do-i-upload-my-survey-data-into-addmaple)\n- [Importing and Preparing Data](/help/preparation/importing-and-preparing-data)\n"},"integrations/tally":{"title":"Tally","category":"Integrations","slug":"integrations/tally","blurb":"Connect your Tally account to AddMaple using an API key and analyze your form responses directly.","order":4,"filename":"tally.md","uid":"integrations/tally","content":"# Tally\n\nAddMaple integrates with Tally, allowing you to analyze your form responses without needing to download and upload files. Your responses sync automatically each time you open your project.\n\n## How to connect\n\n### 1. Create a Tally API key\n\nBefore connecting, you'll need to create an API key in your Tally account:\n\n1. Go to [Tally Settings → API keys](https://tally.so/settings/api-keys)\n2. Click **Create API key**\n3. Copy the generated key (it starts with `tly-`)\n\n> **Important**: Store your API key securely. You won't be able to see it again after creation.\n\n### 2. Start a new project in AddMaple\n\nSign in to AddMaple and go to the **New Project** page.\n\n### 3. Click \"Tally\" in the cloud services section\n\nUnder **Connect cloud service**, click the **Tally** option.\n\n\n\n### 4. Enter your API key\n\nA dialog will appear asking for your Tally API key. Paste the key you created in step 1 and click **Connect**.\n\nAddMaple will validate your API key by fetching your forms list.\n\n### 5. Select a form\n\nAfter validation, you'll see a list of all your Tally forms. Click on the form you want to analyze.\n\n### 6. Start analyzing\n\nAddMaple will fetch your submissions and automatically:\n\n- Detect column types (text, numbers, categories, dates)\n- Merge multi-select questions into single columns\n- Generate readable column names\n- Create initial charts and summaries\n\n## Keeping data in sync\n\nEach time you open your Tally project in AddMaple, it fetches the latest submissions. There's no need to manually refresh or re-upload data.\n\n## Supported question types\n\nAddMaple handles all Tally question types:\n\n| Tally Type | AddMaple Type |\n|------------|---------------|\n| Text Input, Textarea, Email, Phone, URL | Text |\n| Multiple Choice (single), Dropdown | Category |\n| Checkboxes, Multi-Select | Multi-Select |\n| Number, Linear Scale, Rating, NPS | Numeric |\n| Date, Time | Date |\n| File Upload | Text (URL) |\n| Matrix | Expanded to individual columns |\n\n## API key security\n\n- Your API key is stored securely and used only to fetch your Tally data\n- AddMaple requests read-only access to your forms and submissions\n- Your actual form responses are processed in your browser and never stored on our servers\n\n## Troubleshooting\n\n### \"Invalid API key\" error\n\nMake sure you copied the complete API key including the `tly-` prefix.\n\n### Empty forms list\n\nYour API key inherits your user permissions. Make sure you have access to the forms you want to analyze in your Tally account.\n\n### API key expired\n\nIf your API key stops working, create a new one in your [Tally settings](https://tally.so/settings/api-keys) and reconnect.\n\n## Further reading\n\n- [Integrations](/help/integrations/overview)\n- [Tally API Keys Documentation](https://developers.tally.so/api-reference/api-keys)\n- [How Do I Upload My Survey Data Into AddMaple](/help/frequently-asked-questions/how-do-i-upload-my-survey-data-into-addmaple)\n- [Importing and Preparing Data](/help/preparation/importing-and-preparing-data)\n"},"integrations/typeform":{"title":"Typeform","category":"Integrations","slug":"integrations/typeform","blurb":"Connect your Typeform account to AddMaple and analyze your survey responses directly without downloading files.","order":2,"filename":"typeform.md","uid":"integrations/typeform","content":"# Typeform\n\nAddMaple integrates directly with Typeform, allowing you to analyze your survey responses without needing to download and upload files. Your responses sync automatically each time you open your project.\n\n## How to connect\n\n### 1. Start a new project\n\nSign in to AddMaple and go to the **New Project** page.\n\n### 2. Click \"Typeform\" in the cloud services section\n\nUnder **Connect cloud service**, click the **Typeform** option.\n\n\n\n### 3. Authorize AddMaple\n\nYou'll be redirected to Typeform to authorize AddMaple to access your forms and responses. Click **Allow** to grant access.\n\nAddMaple requests read-only access to:\n\n- Your forms (to show you a list to choose from)\n- Your responses (to analyze the data)\n\n### 4. Select a form\n\nAfter authorization, you'll see a list of all your Typeform surveys. Click on the form you want to analyze.\n\n### 5. Start analyzing\n\nAddMaple will fetch your responses and automatically:\n\n- Detect column types (text, numbers, categories, dates)\n- Merge multi-select questions into single columns\n- Generate readable column names\n- Create initial charts and summaries\n\n## Keeping data in sync\n\nEach time you open your Typeform project in AddMaple, it fetches the latest responses. There's no need to manually refresh or re-upload data.\n\n## Reconnecting\n\nIf your Typeform authorization expires, AddMaple will prompt you to re-authorize. Simply click the **Re-authorize** button and follow the same authorization flow.\n\n## Supported question types\n\nAddMaple handles all Typeform question types:\n\n| Typeform Type | AddMaple Type |\n|---------------|---------------|\n| Short Text, Long Text, Email | Text |\n| Multiple Choice (single) | Category |\n| Multiple Choice (multiple) | Multi-Select |\n| Opinion Scale, Rating | Numeric |\n| Yes/No | Boolean |\n| Date | Date |\n| Number | Numeric |\n| Matrix | Expanded to individual columns |\n\n## Privacy\n\nYour Typeform data is processed in your browser. AddMaple stores only the connection credentials needed to fetch your data—your actual survey responses are never stored on our servers.\n\n## Further reading\n\n- [Integrations](/help/integrations/overview)\n- [How Do I Upload My Survey Data Into AddMaple](/help/frequently-asked-questions/how-do-i-upload-my-survey-data-into-addmaple)\n- [Importing and Preparing Data](/help/preparation/importing-and-preparing-data)\n"},"legend/clean-with-ai":{"title":"How to use Clean with AI","category":"Legend","slug":"legend/clean-with-ai","blurb":"Use AI to automatically clean and standardize messy category labels in your survey data.","order":3,"filename":"clean-with-ai.md","uid":"legend/clean-with-ai","content":"# How to use Clean with AI\n\nSurvey data often contains messy category labels: spelling differences, inconsistent capitalization, multiple variants of the same response, or unordered scales (e.g. \"Strongly Agree\" appearing before \"Disagree\").\n\nThe **Clean with AI** feature in the legend helps standardize these categories. It can rename, order, and optionally merge categories automatically.\n\n---\n\n### Where to find it\nYou can run Clean with AI from the **Legend**:\n- **In a pivot chart:** click the **Legend** tab on the right.\n- **In Manage Column(s):** open the column details and **scroll to the Legend**.\n\n\n\n---\n\n### How it works\nWhen you click **Clean categories with AI**, a dialog appears with two options:\n- **Allow Category Merging** – Off by default. Tick this if you want the AI to merge near-duplicate categories.\n- **Additional instructions** – A text area where you can guide the AI (for example: *\"Keep age categories in ascending order\"* or *\"Do not merge 'Other' with anything else\"*).\n\nClick **Start** to generate suggestions.\n\n\n\nThe AI will then:\n- Suggest **renames** for inconsistent or unclear category labels.\n- Suggest an **order** (e.g. arranging Likert responses from negative → positive, or ordering age ranges correctly).\n- Optionally suggest **merges** (if **Allow Category Merging** was ticked).\n\n---\n\n### Applying changes\n1. Review the suggestions in the preview.\n2. Choose whether to accept the proposed renames, ordering, and (if enabled) merges.\n3. Click **Apply**.\n4. **Save** your changes to update the project.\n\n---\n\n### Viewing mappings\nIf categories are merged, click **View Mappings** in the legend to see how the original raw categories map to the new ones.\n\n---\n\n### Example\nA survey column for \"Opinion\" includes responses:\n- \"agree\"\n- \"Strongly Agree\"\n- \"disagree\"\n- \"Neutral\"\n\nUsing **Clean with AI** (with merging **off**):\n- Categories are renamed for consistency (\"Agree,\" \"Strongly agree,\" \"Disagree,\" \"Neutral\").\n- The order is adjusted to: **Disagree → Neutral → Agree → Strongly agree**.\n\nUsing **Clean with AI** (with merging **on** and instruction *\"Merge near-duplicates\"*):\n- If \"Yes,\" \"Y,\" and \"Yep\" are present, they are merged into a single **Yes** category.\n\n---\n\n### Key points\n- Clean with AI can **rename**, **order**, and optionally **merge** categories.\n- By default, only **renaming and ordering** are applied.\n- Tick **Allow Category Merging** if you want AI to merge categories.\n- Add **optional instructions** to guide the AI.\n- All changes persist for the column and carry through to exports.\n- You can **reset to the original** data at any time.\n\n---\n"},"legend/legend":{"title":"How to work with legends","category":"Legend","slug":"legend/legend","blurb":"Learn how to manage chart legends by renaming, reordering, merging, and recoloring categories in your data.","order":1,"filename":"legend.md","uid":"legend/legend","content":"# How to work with legends\n\nLegends control how categories are displayed in charts and pivot tables. They are the place to rename, reorder, merge, recolor, and otherwise manage how your data appears. \n\nYou can open the legend in two ways: \n- In a pivot chart: click the **Legend** tab on the right-hand panel \n- In [Manage Column(s)](../preparation/manage-columns): open the column details view and switch to the **Legend** tab \n\n---\n\n### Actions in the legend\n\nYou can do the following: \n\n- **Rename categories** – Click a category name to edit it. \n- **Reorder categories** – Drag to reorder, or click **Reverse Order** to flip the list. \n- **Hide or show categories** – Click the **hide icon** next to a category to exclude it, or the **show icon** to bring it back. \n- **Merge categories** – Select two or more categories (click one at a time or use Shift to select a range), then click **Merge**. \n- **Assign colors** – Click a category's color swatch to assign: \n - A completely custom color \n - A color from your current preset \n - The preset applied to all remaining categories for that column \n- **Ordered vs Independent** – Toggle between: \n - **Ordered Categories** (treat categories as ordinal, e.g. Likert scales) \n - **Independent Categories** (treat categories as nominal, e.g. segments) \n- **Clean with AI** – Automatically renames, orders, and optionally merges categories. \n- **Reset to original** – Restore the legend to match the raw data. \n\n---\n\n### Saving and persistence\n- After making changes, click **Save**. The chart will update immediately. \n- Changes are **persisted for the column**, not just for one chart. \n - Example: if you assign custom colors to segment categories, those colors will appear consistently across all charts and exports whenever you pivot by that column. \n\n \n\n---\n\n### Viewing mappings\nIf you have renamed or merged categories, click **View Mappings** to see how the original categories from the raw data have been mapped to the new ones. \n\n \n\n---\n\n### Limitations\n- Numeric bins and date bins cannot be edited in the legend. For these, the legend is **read-only**. \n- To change bins, use [Custom binning](../preparation/number-binning). \n\n---\n\n### Example\nA survey export includes a text column for \"Region\" with inconsistent values: \"U.S.,\" \"USA,\" \"United States.\" \n- In the legend, select all three and click **Merge**. \n- Rename the merged category \"United States.\" \n- Assign a custom blue color from your preset. \n- Save your changes. \n\nAll charts and exports will now show a clean, consistent \"United States\" category. \n\n---\n\n### Key points\n- Legends are the central place to clean, reorder, and recolor categories. \n- All changes persist across your project and carry into exports. \n- Numeric and date bins cannot be adjusted from the legend. \n\n---\n"},"legend/merging-categories":{"title":"How to merge categories","category":"Legend","slug":"legend/merging-categories","blurb":"Learn how to merge duplicate or similar categories in your data to create cleaner, more consistent results.","order":5,"filename":"merging-categories.md","uid":"legend/merging-categories","content":"# How to merge categories\n\nSometimes survey data contains multiple categories that represent the same thing — for example, \"U.S.,\" \"USA,\" and \"United States.\" Merging lets you combine these into a single clean category. \n\n---\n\n### Where to find it\n\nYou can merge categories in the **Legend**:\n- **In a pivot chart:** click the **Legend** tab on the right. \n- **In Manage Column(s):** open the column details and **scroll to the Legend**. \n\n \n\n---\n\n### How to merge\n\nIn the legend, select the categories you want to merge. You can click categories one at a time, or hold **Shift** to select a range. \n\n \n \nClick the **Merge** button and a pop up will appear where you can choose the label for your merged category.\n\n \n\nThe selected categories will collapse into one merged category. \n\n \n\n \n\n---\n\n### Viewing mappings\n\nAfter merging, you can click **View Mappings** to see how the original raw categories have been mapped to the new merged category. \n\n \n\n---\n\n### Undoing a merge\n\nTo undo a merge, click the \"Reset\" button. This will return your categories to their original state. \n\n---\n\n### Keeping original categories\n\nMerging inside the legend changes the categories for that variable everywhere in the project. \nIf you want to **keep the original categories as well as create a merged version**, use a [Custom Column](../data-types/create-segment). This allows you to define a new variable that merges categories across one or more columns, without altering the original. \n\n---\n\n### Example\n\nA survey column for \"Region\" includes responses: \n- \"U.S.\" \n- \"USA\" \n- \"United States\" \n\nTo merge them: \n1. Select all three categories in the legend. \n2. Click **Merge**. \n3. Rename the result **United States**. \n\nThe legend now shows one clean category, and charts and exports will treat all three raw values as the same. \n\n---\n\n### Key points\n\n- Merging combines two or more categories into one. \n- Use **View Mappings** to track how raw values map to merged categories. \n- Use [Custom Columns](../data-types/create-segment) if you want to create a merged version while keeping the originals intact. \n- Changes persist across the project and carry into exports. \n\n---\n"},"legend/ordered-vs-independent":{"title":"Ordered vs Independent categories","category":"Legend","slug":"legend/ordered-vs-independent","blurb":"Learn how to toggle between ordered and independent categories to unlock Likert charts or treat variables as nominal.","order":4,"filename":"ordered-vs-independent.md","uid":"legend/ordered-vs-independent","content":"\n# Ordered vs Independent categories\n\nIn AddMaple, you can choose whether a categorical variable should be treated as **Ordered Categories** or **Independent Categories**. \n\n- **Ordered Categories** – categories have a natural order (e.g. Strongly disagree → Strongly agree, or age ranges). \n- **Independent Categories** – categories have no inherent order (e.g. regions, product types, segments). \n\n---\n\n### Where to find it\n\nYou can set this in the **Legend**:\n- **In a pivot chart:** click the **Legend** tab on the right. \n- **In Manage Column(s):** open the column details and **scroll to the Legend**. \n\n\n\n---\n\n### Auto-detection\n\nAddMaple automatically detects many common Likert-style scales and sets these as **Opinion Scale** columns. This makes them ordered by default, so you can immediately use them in Likert charts. \n\nYou can also use the Ordered/Independent toggle on other categorical columns, such as **Single Select** questions. For example, a single-select column with age ranges or satisfaction levels can be switched to **Ordered Categories** to unlock Likert-style analysis. \n\n---\n\n### Ordered Categories\n\nWhen categories are set to **Ordered**, AddMaple enables **Likert charts**: \n- By default, Likert charts center on the neutral category. \n- You can adjust to left-align instead, depending on how you want to display results. \n- Likert charts are percentage-based and are a great way to compare distributions across multiple items. \n\n \n \n \n\nTo view a Likert-style chart, you need to: \n- **Pivot** the ordered column by another column (e.g. Satisfaction by Age Group), or \n- **Group multiple columns together** (e.g. a set of related opinion questions). \n\nWhen you switch a column to **Ordered Categories**, three default groups appear in the legend: \n- **Negative** \n- **Neutral** \n- **Positive** \n\nYou can drag individual categories into the appropriate group. You can also hover over a group title to edit it — for example, renaming them to **Low Income, Medium Income, High Income** when working with income bands. \n\nTypical use cases for Ordered Categories: \n- Opinion scales (Strongly disagree → Strongly agree) \n- Ratings (Poor → Excellent) \n- Ordered ranges (e.g. Low → Medium → High, or income bands) \n- Age brackets (18–24 → 25–34 → 35–44 …) \n\n---\n\n### Independent Categories\nWhen categories are set to **Independent**, AddMaple will treat them as separate, unordered items: \n- Shown in bar, column, or other categorical charts \n- Order can still be adjusted manually in the legend, but there is no assumed ranking \n- Useful for categories like countries, products, or customer segments \n\n \n\n---\n\n### Switching modes\n1. Open the legend for a variable. \n2. Toggle between **Ordered Categories** and **Independent Categories**. \n3. Click **Save** to update. \n\nThe change applies project-wide for that variable, including in exports. \n\n---\n\n### Example\nA survey question asks respondents to rate satisfaction: \"Very dissatisfied,\" \"Dissatisfied,\" \"Neutral,\" \"Satisfied,\" \"Very satisfied.\" \n\n- If treated as **Independent Categories**, these appear as a standard bar chart. \n- If switched to **Ordered Categories**, you can use a Likert chart, centered on \"Neutral.\" \n- To view it as a Likert chart, pivot Satisfaction by another column (e.g. Age Group), or group several opinion questions together. \n- In the legend, drag \"Very dissatisfied\" and \"Dissatisfied\" into the **Negative** group, keep \"Neutral\" in its group, and place \"Satisfied\" and \"Very satisfied\" into the **Positive** group. \n\nThis makes it much easier to compare satisfaction distributions across multiple questions. \n\n---\n\n### Key points\n- AddMaple automatically detects many Likert-style scales and sets them as **Opinion Scale** (ordered) by default. \n- You can also switch other categorical variables, such as **Single Select** columns, to ordered when a meaningful order exists. \n- Ordered categories enable **Likert charts**, but you need to **pivot by another column** or **group multiple columns** to see them. \n- Ordered mode creates three editable groups (Negative, Neutral, Positive) where you can drag categories and rename group labels. \n- Independent categories are treated as separate, unordered items. \n- The setting applies across the project and exports. \n\n---\n"},"pivot-chart-and-table/additional-charts":{"title":"Additional Charts","category":"Pivot Chart and Table","slug":"pivot-chart-and-table/additional-charts","blurb":"Access pie charts, scatter plots, stacked bar charts, and geographic maps through the More Charts option.","order":6,"filename":"additional-charts.md","uid":"pivot-chart-and-table/additional-charts","content":"\n# Additional Charts\n\nWhen viewing a single column in AddMaple, you can access additional chart types beyond the default horizontal bar chart. These specialized visualizations help you explore your data in different ways. Learn more about [why AddMaple uses horizontal bar charts](../frequently-asked-questions/why-do-you-use-horizontal-bar-charts).\n\n## Accessing Additional Charts\n\nTo view additional chart options:\n\n1. **Select a single column** — Make sure you're viewing data for just one column (not multiple columns)\n2. **Click \"More Charts\"** — Look for the \"More Charts\" option on the left side of your screen\n3. **Choose your chart type** — Select from the available options\n\n\n\n## Available Chart Types\n\n### Pie Charts\n\nPerfect for showing proportions and percentages. Includes three variants:\n- **Pie** — Standard pie chart\n- **Donut** — Pie chart with a hollow center\n- **Rose** — Radial chart where segment radius represents values\n\nPie charts work best with categorical data and automatically merge smaller categories into \"Other\" to keep the visualization clean.\n\n\n\n## Using Aggregation with Additional Charts\n\nYou can combine additional charts with [aggregation](../sentence-builder/aggregation) to create more sophisticated visualizations. For example:\n\n- **Aggregated pie charts** — Show median salary by department, or average satisfaction by region\n- **Geographic maps with aggregation** — Display total sales by country, or median income by state\n- **Rose charts with totals** — Visualize sum of values across different categories\n\nTo use aggregation with additional charts:\n1. Set up your aggregation (Total, Average, Median, or Count Unique) using the \"Number of\" button\n2. Select your aggregation column (numeric columns for totals/averages/medians, categorical for count unique)\n3. Choose your additional chart type from \"More Charts\"\n\nThe aggregation will apply to your chosen chart type, giving you powerful ways to explore relationships in your data.\n\n\n### Geographic Maps\n\nWhen AddMaple detects geographic data (countries, states, provinces), you'll see a map option. The system automatically:\n\n- **Detects geographic scope** — Recognizes if your data contains countries, US states, Canadian provinces, or European countries\n- **Creates interactive maps** — Shows your data overlaid on the appropriate geographic region\n- **Includes a bar chart** — Displays the top 15 locations alongside the map for easy comparison\n- **Uses color coding** — Applies your project's color scheme to represent data values\n\n\n\n\n---\n\n### Key points\n- Additional charts are only available when viewing a single column\n- Geographic maps appear automatically when geographic data is detected\n- All charts respect your project's color settings and weighting\n- Chart settings can be customized for each visualization type\n\n---\n"},"pivot-chart-and-table/boxplots-mean-dot-plots":{"title":"Box Plots and Mean Dot Plots","category":"Pivot Chart and Table","slug":"pivot-chart-and-table/boxplots-mean-dot-plots","blurb":"Visualize numeric data distributions with box plots and mean dot plots for statistical analysis and comparison.","order":5,"filename":"boxplots-mean-dot-plots.md","uid":"pivot-chart-and-table/boxplots-mean-dot-plots","content":"\n# Box Plots and Mean Dot Plots\n\nBox plots and mean dot plots are powerful visualizations for exploring numeric data distributions. They help you understand the spread, central tendency, and outliers in your data.\n\n## When to Use Box Plots and Mean Dot Plots\n\nThese visualizations are available for:\n\n- **Single numeric column** — Explore the distribution of one numeric variable\n- **Groups of numeric columns** — Compare distributions across multiple numeric variables\n- **Categorical vs numeric** — Compare numeric distributions across different categories\n\n## Box Plots\n\nBox plots show the complete statistical distribution of your data in a compact format:\n\n- **Box** — Shows the interquartile range (Q1 to Q3), representing the middle 50% of your data\n- **Median line** — The white line inside the box shows the median (50th percentile)\n- **Whiskers** — Extend from Q1 to minimum and from Q3 to maximum values\n- **End caps** — Mark the actual minimum and maximum values in your dataset\n\n\n\n### Understanding Box Plot Components\n\nWhen you hover over a box plot, you'll see detailed statistics including:\n- **Mean** — Average value\n- **Median** — Middle value (50th percentile)\n- **Min/Max** — Lowest and highest values\n- **Q1/Q3** — First and third quartiles (25th and 75th percentiles)\n- **Standard Deviation** — Measure of data spread\n- **Count** — Number of data points\n- **Non-Zero Count** — Number of non-zero values\n\n## Mean Dot Plots\n\nMean dot plots show the average (mean) value for each category or group:\n\n- **Dots** — Each dot represents the mean value for that category\n- **Position** — Dot position along the scale shows the actual mean value\n- **Color coding** — Uses your project's color scheme for easy identification\n\n\n\n## Accessing Box Plots and Mean Dot Plots\n\nThe controls and options vary depending on what columns you're viewing:\n\n### Categorical vs Numeric OR Single Numeric\n\nWhen viewing categorical vs numeric data or a single numeric column:\n\n1. **Key Stats | Ranges control** — Located on the left side of your screen\n2. **Default is \"Ranges\"** — Shows numeric data in bins (grouped ranges)\n3. **Select \"Key Stats\"** — This reveals additional visualization options\n4. **Box Plot | Mean control** — Appears after selecting \"Key Stats\"\n - Choose **Box Plot** for complete distribution visualization\n - Choose **Mean** for average value comparisons\n\n\n\n### Grouped Numeric Columns\n\nWhen viewing multiple numeric columns together:\n\n1. **Box Plot | Mean control** — Located directly on the left side\n2. **Default is \"Box Plot\"** — Shows complete statistical distributions\n3. **Alternative is \"Mean\"** — Shows average values for quick comparison\n\n## Additional Controls\n\n### Display Format\n- **Integer | Decimal** — Choose whether to show whole numbers or decimal places\n- **Show Numbers on Chart** — Toggle to display actual values on the visualization\n\nThese controls help you customize how your data appears and make it easier to read specific values.\n\n## Interactive Features\n\n### Scale and Values\n\n- **Actual values** — The scale shows real data values, not percentages\n- **Reference markers** — Gray markers at 0%, 50%, and 100% help you read values\n- **Hover tooltips** — Show exact values and complete statistical summaries\n\n### Sorting Options\n\nYou can sort your visualizations by:\n- **Label** — Alphabetical order\n- **Value** — By median (box plots) or mean (dot plots)\n- **Direction** — Ascending or descending order\n\n### Color and Styling\n\n- **Project colors** — Respects your project's color settings\n- **Alternating rows** — Subtle background shading helps distinguish between rows\n- **Full width** — Single-column box plots use the full width for better visibility\n\n## Best Practices\n\n**Choose the right visualization:**\n- Use **box plots** when you want to see the complete distribution, including outliers\n- Use **mean dot plots** when you want to focus on average values and make quick comparisons\n\n**Interpret your results:**\n\n- **Wide boxes** indicate high variability in your data\n- **Narrow boxes** suggest consistent values\n- **Outliers** appear as points beyond the whiskers\n- **Skewed distributions** show when the median is closer to one end of the box\n\n\n---\n\n### Key points\n- Box plots show complete statistical distributions with quartiles and outliers\n- Mean dot plots focus on average values for quick comparisons\n- Both visualizations work with single columns, grouped columns, or categorical comparisons\n- Interactive tooltips provide detailed statistical information\n- Sorting and styling options help you explore your data effectively\n\n---\n"},"pivot-chart-and-table/bubble-dot-plots":{"title":"Dot Charts","category":"Pivot Chart and Table","slug":"pivot-chart-and-table/bubble-dot-plots","blurb":"Create interactive dot charts (also known as bubble charts) to visualize numeric data distributions with automatic or custom scaling options.","order":6,"filename":"bubble-dot-plots.md","uid":"pivot-chart-and-table/bubble-dot-plots","content":"\n# Dot Charts\n\nDot charts (also commonly known as bubble charts) provide powerful ways to visualize numeric data distributions and comparisons. These visualizations show data points as circular elements positioned according to their values, making it easy to see patterns, outliers, and distributions at a glance.\n\n## When to Use Dot Charts\n\nThese visualizations (also commonly known as bubble charts) are ideal for:\n\n- **Numeric data exploration** — See the spread and distribution of numeric values\n- **Comparative analysis** — Compare values across different categories or groups\n- **Statistical insights** — Identify patterns, outliers, and trends in your data\n- **Interactive exploration** — Hover over dots to see detailed statistics\n\n## Types of Dot Charts\n\nAddMaple offers several types of dot chart visualizations (also commonly known as bubble charts):\n\n### Regular Bubble Charts\nShow data points as bubbles positioned along a scale, with size and position representing values.\n\n### Percentage-Based Bubble Charts\nDisplay values as percentages of totals, with bubbles positioned relative to percentage values.\n\n### Column Percentage Bubble Charts\nShow each column's values as percentages relative to that specific column's total.\n\n### Sample Percentage Bubble Charts\nDisplay values as percentages relative to the total sample size.\n\n## Accessing Dot Chart Controls\n\nThe controls and options vary depending on your data configuration:\n\n### Two-Column Pivot (Categorical vs Categorical)\n\nWhen viewing two categorical columns:\n\n1. **Count | Percentage | Proportional control** — Located on the left side\n2. **Select \"Percentage\"** — This activates percentage-based visualization\n3. **Stacked | Bar | Dot control** — Appears after selecting Percentage\n4. **Choose \"Dot\"** — This creates a dot chart\n5. **Bubble Scale control** — Appears when conditions are met (see below)\n\n### Two-Column Pivot (Categorical vs Numeric)\n\nWhen viewing a categorical column against a numeric column:\n\n1. **Count | Percentage | Proportional control** — Located on the left side\n2. **Select \"Percentage\"** — This activates percentage-based visualization\n3. **Stacked | Bar | Dot control** — Appears after selecting Percentage\n4. **Choose \"Dot\"** — This creates a dot chart\n5. **Bubble Scale control** — Appears when conditions are met (see below)\n\n**Note:** This is the most common scenario for dot charts with bubble scale controls.\n\n### Grouped Numeric Columns\n\nWhen viewing multiple numeric columns together:\n\n1. **Box Plot | Mean control** — Located directly on the left side\n2. **Choose \"Mean\"** — Creates a dot chart visualization showing the means\n3. **Bubble Scale control** — Appears when switching to percentage mode\n\n### Grouped Pivot Charts (Numeric Opinion Scale)\n\nWhen working with grouped pivot charts:\n\n1. **Select a numeric opinion scale column** — The pivot column must be a numeric rating scale (e.g., 1-5, 1-7, 1-10)\n2. **Enable group pivot mode** — Use the group pivot controls in the left sidebar\n3. **Choose aggregation method** — Select \"Mean\" or \"Median\" for the group pivot type\n4. **Switch to dot visualization** — The system will display dot charts showing the average values for each group\n\n**Note:** Grouped pivot dot charts use a different approach and do not show the bubble scale control.\n\n### Single Numeric Column\n\nYou can also create dot charts for a single numeric column, but this scenario is less commonly used:\n\n1. **Key Stats | Ranges control** — Located on the left side\n2. **Select \"Key Stats\"** — Reveals additional visualization options\n3. **Box Plot | Mean control** — Choose \"Mean\" for dot chart visualization\n\n## Bubble Scale Control\n\nThe bubble scale control determines how dot positions are calculated and displayed:\n\n### Fixed Scale (0–100)\n- **Default setting** — Dots are positioned on a fixed 0-100 scale\n- **Consistent comparison** — All charts use the same scale for easy comparison\n- **Predictable positioning** — You always know what 0%, 50%, and 100% represent\n- **Automatic activation** — Used when auto scale conditions aren't met\n\n### Auto Scale\n- **Data-driven scaling** — Scale adjusts automatically based on actual data values\n- **Optimal visualization** — Shows data distribution most clearly for each chart\n- **Variable ranges** — Each chart may have different min/max values\n- **Better for exploration** — Reveals actual data patterns and outliers\n\n## NPS Dot Plots\n\nIf your numeric column is detected as an NPS score (0–10), AddMaple can show an NPS dot plot:\n\n- **Fixed scale**: -100 to 100\n- **Auto scale**: uses the observed NPS range in your filtered data\n- **Scale formatting**: NPS is a score (not a percent), so the scale does not show `%`\n- **Legend**: hidden in NPS mode\n\n## When Bubble Scale Control Appears\n\nThe bubble scale control is only available when specific conditions are met:\n\n### Required Conditions\n- **Dot chart mode** — Must be in Dot mode (not Stacked or Bar)\n- **Percentage mode** — Must have Percentage or Proportional selected\n- **Two pivots** — Requires at least two columns (typically categorical vs numeric)\n- **No special modes** — Cannot be in time series, word cloud, or scatter plot mode\n\n### Visibility Rules\n- **Single pivot charts** — Control is hidden (requires two pivots for meaningful scaling)\n- **Count mode** — Control is hidden (only relevant for percentage-based charts)\n- **Grouped pivot charts** — Control is hidden (grouped pivot dot plots use a different approach and don't require scale controls)\n\n## Interactive Features\n\n### Scale and Positioning\n- **Reference markers** — Gray markers at 0%, 50%, and 100% help you read values\n- **Actual values** — Bubbles are positioned according to real data values\n- **Responsive scaling** — Auto scale adjusts dynamically as you filter data\n\n### Hover Information\n- **Exact values** — Hover over bubbles to see precise numeric values\n- **Statistical context** — See how each value relates to the overall distribution\n- **Category information** — Understand which category each bubble represents\n\n### Visual Styling\n- **Color coding** — Uses your project's color palette for consistency\n- **Size consistency** — All bubbles have the same size for clear comparison\n- **Interactive feedback** — Bubbles highlight on hover for better visibility\n\n## Switching Between Scale Types\n\n### From Fixed to Auto Scale\n1. **Locate the control** — Find \"0–100 | Auto Scale\" in the left sidebar\n2. **Select \"Auto Scale\"** — The dot chart immediately updates\n3. **Observe changes** — Scale adjusts to show data distribution more clearly\n4. **Compare results** — Notice how the range changes to fit your data\n\n### From Auto to Fixed Scale\n1. **Select \"0–100\"** — Returns to the standard fixed scale\n2. **Consistent comparison** — All dot charts now use the same 0-100 range\n3. **Predictable positioning** — You always know what the scale represents\n\n## Best Practices\n\n### Choose the Right Scale Type\n- **Use Auto Scale** when exploring individual datasets and want to see the full data distribution\n- **Use Fixed Scale** when comparing multiple dot charts and need consistent reference points\n- **Consider your audience** — Fixed scale is easier for audiences to understand quickly\n\n### Interpret Your Results\n- **Wide distribution** — If dots spread across most of the scale, your data has high variability\n- **Clustered dots** — If dots cluster in one area, your data has low variability\n- **Outliers** — Dots positioned far from others may indicate data outliers\n- **Empty areas** — Gaps in the scale show missing or sparse data ranges\n\n### Optimize for Analysis\n- **Combine with filtering** — Use filters to focus on specific data ranges\n- **Sort by value** — Arrange categories to see patterns more clearly\n- **Compare across charts** — Use fixed scale when comparing multiple dot charts\n- **Export findings** — Save dot charts with auto scale when sharing detailed analysis\n\n## Troubleshooting\n\n### Bubble Scale Control Not Visible\n- **Check chart mode** — Must be in Dot mode (not Stacked or Bar)\n- **Verify percentage setting** — Must have Percentage or Proportional selected\n- **Confirm data structure** — Need at least two pivots for scale control\n\n### Dots Not Displaying Correctly\n- **Refresh data** — Try switching between chart modes to reload\n- **Check data types** — Ensure columns contain numeric data\n- **Verify settings** — Make sure dot chart mode is properly enabled\n- **Clear filters** — Remove any filters that might hide data\n\n### Scale Issues\n- **No auto scale option** — Ensure you're in percentage mode\n- **Unexpected ranges** — Fixed scale always uses 0-100, auto scale adjusts to data\n- **Inconsistent positioning** — Use fixed scale for consistent comparison across dot charts\n\n## Key Points\n- Dot charts (also known as bubble charts) show numeric distributions as circular elements\n- Four main scenarios: two-column pivot (categorical vs categorical), two-column pivot (categorical vs numeric), grouped numeric columns, and grouped pivot charts\n- Scale controls determine how dot positions are calculated\n- Fixed scale (0–100) provides consistent comparison\n- Auto scale adjusts dynamically to show data distribution\n- Grouped pivot dot charts require numeric opinion scale columns and mean/median aggregation\n- Bubble scale controls appear only in percentage mode + dot mode\n- Controls only appear when specific conditions are met\n- Interactive features provide detailed value information\n- Choose scale type and chart type based on your analysis goals\n\n---\n\n### Key takeaways\n- Four main scenarios for dot charts: two-column pivot (categorical vs categorical), two-column pivot (categorical vs numeric), grouped numeric columns, and grouped pivot charts\n- Grouped pivot dot charts require numeric opinion scale columns with mean/median aggregation\n- Bubble scale controls appear only in specific chart configurations (percentage mode + dot mode)\n- Fixed scale (0–100) is best for consistent comparison across multiple dot charts\n- Auto scale is ideal for exploring individual data distributions in detail\n- Interactive tooltips provide detailed statistical information\n- Consider your data type and analysis goals when choosing chart type and scale\n- Troubleshooting steps help resolve common visibility and configuration issues\n\n---"},"pivot-chart-and-table/editcategory":{"title":"Editing a Category","category":"Pivot Chart and Table","slug":"pivot-chart-and-table/editcategory","blurb":"Rename categories from the Edit tab; updates apply immediately without altering your original data.","order":3,"filename":"editcategory.md","uid":"pivot-chart-and-table/editcategory","content":"# Editing a Category\n\nWith AddMaple, you can easily rename categories without altering your original data. The changes are saved in your project settings, so the original data remains untouched.\n\nTo rename a category, expand the column containing the category, click the \"Edit\" tab in the legend, locate the category you want to update, and click the pencil icon.\n\n\nAdjust the name of the category and when you are done press enter or click the green tick.\n\n\nOnce you rename a category, the change will be applied instantly, and your pivot chart will update automatically to reflect the new name.\n"},"pivot-chart-and-table/explain-chart":{"title":"AI Powered Chart Explanations","category":"Pivot Chart and Table","slug":"pivot-chart-and-table/explain-chart","blurb":"Click Explain Chart to get an AI-generated summary of what the current chart shows.","order":4,"filename":"explain-chart.md","uid":"pivot-chart-and-table/explain-chart","content":"# AI Powered Chart Explanations\n\nWhile viewing any chart in AddMaple, whether a single or multiple pivot, you can get an AI powered explanation.\n\nSimply click the **Explain Chart **button and wait as the explanation appears on the right of your screen.\n\n"},"pivot-chart-and-table/filter-types":{"title":"Use Filter Types","category":"Pivot Chart and Table","slug":"pivot-chart-and-table/filter-types","blurb":"Reference every AddMaple filter option with the column types it supports and practical examples.","order":8,"filename":"filter-types.md","uid":"pivot-chart-and-table/filter-types","content":"\n# Use filter types\n\nUse this reference whenever you need to choose the right filter for a column. Every filter here removes respondent rows from your dataset before any charts, tables, or exports run. The table lists the label you see in the filter menu, the supported column types, and a quick example so you can apply it with confidence.\n\n| Filter label | Column types | What it does | Example |\n| --- | --- | --- | --- |\n| is equal to | Numeric | Keeps rows where the numeric value matches exactly. | Show only respondents with `Score = 5`. |\n| is not equal to | Numeric | Removes rows where the value matches exactly. | Exclude `Age = 18` respondents. |\n| is between | Numeric, Date | Keeps rows within the start (inclusive) and before the end (exclusive) of a range. On dates, the filter automatically matches the granularity of the inputs. | Limit to `Satisfaction between 6 and 8`, or `Date between 2024-01-01 and 2024-03-01`. |\n| is greater than or equal to | Numeric | Keeps rows with values ≥ the number you enter. | Include scores of `4` or higher. |\n| is greater than | Numeric | Keeps rows with values strictly greater than the number you enter. | Focus on `Spend > 500`. |\n| is less than or equal to | Numeric | Keeps rows with values ≤ the number you enter. | Review respondents with `NPS ≤ 0`. |\n| is less than | Numeric | Keeps rows with values strictly less than the number you enter. | Highlight orders with `Quantity < 5`. |\n| is | Categorical (single-select) | Keeps rows where the category matches the selection. | View only `Country = Canada`. |\n| is not | Categorical (single-select) | Removes rows where the category matches the selection. | Exclude `Plan = Free`. |\n| has more than | Categorical (single-select) | Keeps rows belonging to categories whose total count is above the threshold; selections that fall below the threshold are filtered out everywhere. | Drop countries with fewer than `50` responses. |\n| contains | Text, Unique ID | Finds rows where the cell contains the phrase (case-insensitive). Wrap the phrase in quotes to match whole words only. | Find feedback mentioning `\"delay\"`. |\n| doesn't contain | Text, Unique ID | Removes rows containing the phrase. Quoted phrases enforce whole-word matching. | Remove comments that say `\"spam\"`. |\n| includes any | Categorical (multi-select) | Keeps rows that contain at least one of the selected options. | Keep respondents who chose either `Email` or `SMS`. |\n| includes all | Categorical (multi-select) | Keeps rows that contain every selected option. | Find respondents who selected both `iOS` and `Android`. |\n| doesn't include | Categorical (multi-select) | Removes rows that contain any of the selected options. | Exclude anyone who picked `Other`. |\n| count is | Categorical (multi-select) | Matches rows where the number of selected options equals the number you enter. | Find respondents who chose exactly `2` features. |\n| count is greater than | Categorical (multi-select) | Matches rows where the number of selected options is greater than the number you enter. | Find respondents who selected `3+` channels. |\n| count is greater than or equal to | Categorical (multi-select) | Matches rows where the number of selected options is ≥ the number you enter. | Include anyone who picked at least `4` interests. |\n| count is less than | Categorical (multi-select) | Matches rows where the number of selected options is less than the number you enter. | Focus on respondents who chose fewer than `2` partners. |\n| count is less than or equal to | Categorical (multi-select) | Matches rows where the number of selected options is ≤ the number you enter. | Capture respondents who chose at most `1` add-on. |\n\n## Date range tips\n\n- When you enter start and end timestamps less than a week apart, AddMaple honors the exact time. Wider ranges automatically compare on whole dates so you do not see partial-day mismatches.\n- Filtering a date column from a chart uses the same `is between` logic. Click a bar to pre-fill the range, then adjust the start or end if needed.\n\n## Text matching tips\n\n- Text filters ignore case by default (`contains` matches `Delay`, `delay`, or `Delayed`).\n- Wrap the value in quotation marks to require a whole-word match. For example, `\"VIP\"` matches `VIP customer` but not `VIPER`.\n- Use `doesn't contain` to keep everything except the phrase you specify—great for removing spammy tags or out-of-scope topics.\n\n## Multi-select guidance\n\n- `has more than` applies to single-select columns; for multi-select questions use the count operators (`count is`, `count is greater than`, etc.) to control how many selections a row must have.\n- Combine `includes all` with a count operator to require specific answers plus additional selections. Example: add `includes all → Enterprise` and `count is greater than or equal to → 3` to focus on complex enterprise customers.\n\n## Combine filters with AND/OR\n\n- The first filter always uses **and** logic. Switch later filters to **or** when you want to match either condition.\n- Grouping happens automatically: AddMaple joins all **and** filters together, while **or** filters within the same column group create broader matches.\n\n## Related guides\n\n- [Filter your data](../frequently-asked-questions/filter-your-data) – step-by-step ways to add filters from charts, tables, and the top menu.\n- [Filtering vs hiding in pivot charts](./filtering-vs-hiding) – understand how filters differ from legend hides and the status line.\n- [How to remove the long tail](../sentence-builder/how-to-remove-long-tail) – practical example using **has more than** to clean up long lists.\n\n"},"pivot-chart-and-table/filtering-vs-hiding":{"title":"Filtering vs Hiding in Pivot Charts","category":"Pivot Chart and Table","slug":"pivot-chart-and-table/filtering-vs-hiding","blurb":"Understand the difference between filtering and hiding data in pivot charts, and learn how to read the status line that shows rows, results, and weighted counts.","order":7,"filename":"filtering-vs-hiding.md","uid":"pivot-chart-and-table/filtering-vs-hiding","content":"\n# Filtering vs hiding in pivot charts\n\nUnderstanding the difference between filtering, hiding, rows and results is the key to reading the status line that appears above every AddMaple pivot. This guide walks through the terminology we use in the app and shows what happens when you combine multiselect columns or weights.\n\n## Filters – drop rows before the pivot runs\n\n- **What they do** – filters remove respondent rows from *every* calculation. Once a row is filtered out it no longer contributes to totals, percentages, significance tests or exports.\n- **Where they apply** – filters live at the top of the workspace (or on the dashboard widgets) and are evaluated before the pivot is built. Learn more about [filtering your data](../frequently-asked-questions/filter-your-data).\n- **What you will see in the status line** – `X rows filtered`. Those rows are excluded from both the “rows” and “results” counts and from any weighted bases.\n\n## Hiding values – suppress categories after the pivot runs\n\n- **What they do** – hiding is a chart-level action. You can hide individual categories from any [legend](../legend/legend). The rows still exist; we simply remove the hidden category from the output so you can focus on the remaining values.\n- **Row-hiding vs result-hiding**\n - **Empty-like categories (`EMPTY`, `.`)** hide entire rows. If a respondent answered ONLY with an empty value, the row disappears from the visible slice. The status line will show `X empty rows hidden`.\n - **All other categories** only hide the matching *results*. The row still counts toward the row base, but any hidden selections are removed from the results count. The status line shows `X results hidden` with an expandable list of the option labels.\n- **Undo and visibility** – hidden categories stay hidden until you toggle them back on from the [legend](../legend/legend).\n\n## Rows vs results\n\n**Rows**\n- **Definition**: Number of respondents (records) contributing to the chart after filters and row-level hides\n- **When they differ**: Rows and results are the same when none of the pivots are multiselect and no empty-like categories are hidden\n\n**Results**\n- **Definition**: Number of counted answers in the displayed columns\n- **When they differ**: Results can exceed rows when a single respondent can select multiple values (multiselect questions) or when you hide only some of a respondent's selections\n\n### Multiselect example\n\n- A respondent answers \"Red\" and \"Blue\" to a [multiselect question](../data-types/multi-select).\n- Rows = 1 (the respondent).\n- Results = 2 (Red and Blue).\n- If you hide “Red”, the row still counts toward the row base, but you now have 1 result (Blue) and the status line reports `1 result hidden (Red)`.\n\n## Weighting and the status line\n\nWhen a [weight column](../preparation/weighting) is active we calculate a weighted version of rows and results:\n\n- **Weighted results** – the sum of the weights applied to every visible result.\n- **Weighted rows** – the weighted base. If the weighted base matches the unweighted row count we omit the “rows” portion for clarity.\n- The status line reads `Weighted: X results` or `Weighted: X results from Y rows` depending on whether the weighted and unweighted row bases match.\n\n## Reading the status line\n\nThe status line aggregates everything discussed above. For example:\n\n```\nShowing 1,431 results from 870 rows\n61 empty rows hidden\n20 results hidden\n• None of the above — 20 results\nWeighted: 1,520.5 results from 905.2 rows\n```\n\nInterpretation:\n\n1. **Showing…** – there are 870 respondents contributing to the visible chart producing 1,431 counted answers (a multiselect scenario).\n2. **Empty rows hidden** – 61 rows were present but contained only empty-like values, so they have been removed from the visible slice.\n3. **Results hidden** – one of the values (“None of the above”) is hidden, removing 20 results.\n4. **Weighted line** – a weight column is active, so we display the weighted bases alongside the unweighted counts.\n\n## Quick checklist\n\n- Use **filters** when you want to permanently narrow the respondent base for all charts. Learn more about [filtering your data](../frequently-asked-questions/filter-your-data).\n- Use **hide** when you want to focus on specific categories within a chart without changing the overall respondent pool. Learn more about [working with legends](../legend/legend).\n- Remember that **rows** represent respondents and **results** represent counted answers.\n- With **multiselect** pivots results often exceed rows.\n- With **weighting** you will see a second line that reports the weighted totals.\n\n"},"pivot-chart-and-table/grouping-columns":{"title":"Grouping Columns","category":"Pivot Chart and Table","slug":"pivot-chart-and-table/grouping-columns","blurb":"Group similar columns with overlapping categories to analyze their totals together; swap rows/columns for clearer comparisons.","order":1,"filename":"grouping-columns.md","uid":"pivot-chart-and-table/grouping-columns","content":"# Grouping Columns\n\nAddMaple supports grouping columns with overlapping categories, which is especially useful for aligning data across similar questions. This grouping often happens automatically for opinion scales, but you can also manage it manually when needed.\n\nThis example demonstrates grouping three different \"mention\" columns. After cleaning the data in AddMaple by merging similar mentions, we'll now show you how to group these columns together so you can explore the grouped totals.\n\nHere are the three \"mention\" columns. While they are not identical, you can see that they contain similar categories.\n\n\nFirst, expand one of the columns you want to group. Then, click the More menu and select \"Group Columns.\"\n\n\nA dropdown will appear in the sentence builder, allowing you to select the columns you'd like to group together. Only columns with overlapping categories will be displayed as options.\n\n\nOften, you'll have more categories than grouped columns. In such cases, it's often more effective to swap the columns and rows. You can easily do this by toggling the \"Swap Columns and Rows\" option on the left side of the pivot chart.\n\nIn this example, swapping the columns and rows allows you to see the artists mentioned across all three grouped columns, ordered by the total mentions.\n"},"pivot-chart-and-table/percentage-types":{"title":"Understanding Percentage Types","category":"Pivot Chart and Table","slug":"pivot-chart-and-table/percentage-types","blurb":"Learn about the three different percentage calculations in AddMaple tables: row percentages, column percentages, and sample percentages.","order":8,"filename":"percentage-types.md","uid":"pivot-chart-and-table/percentage-types","content":"\n# Understanding Percentage Types\n\nAddMaple provides three different ways to calculate percentages in [pivot tables and charts](../frequently-asked-questions/how-to-pivot-your-data). Each percentage type answers a different question about your data and helps you understand relationships from different perspectives.\n\n## Working with Percentages in AddMaple\n\n### Percentage Base Selection (Charts)\n\nWhen viewing a pivot chart, you can choose which percentage base to display using the **Percentage Base** control in the left menu:\n\n- **Column A** - Shows row percentages (how each row distributes across columns)\n- **Column B** - Shows column percentages (how each column is composed of rows)\n- **All Rows** - Shows sample percentages (percentage of the entire dataset)\n\nThis control appears when you switch from **Count** to **Percentage** mode in the chart menu.\n\n### Cell Tooltips (All Views)\n\nWhen you hover over any cell in a chart or table, AddMaple shows a detailed tooltip that includes:\n\n- The primary metric you've selected (count or percentage)\n- **All three percentage types** (row, column, and sample percentages)\n- The underlying counts and denominators\n- [Statistical significance](../stats/significance-testing) indicators (when enabled)\n\nThis lets you quickly see the data from multiple perspectives without changing your view settings.\n\n### Column Visibility (Tables)\n\nIn pivot tables, you can customize which columns to display:\n\n- Show or hide individual percentage columns (row %, column %, sample %)\n- Show or hide count columns (results, rows, weighted values)\n- Toggle statistical columns ([z-scores, p-values](../stats/significance-testing))\n\nUse the column visibility controls in the table header to customize your view.\n\n## The Three Percentage Types\n\n### Row Percentage (Column A Percent)\n**What it shows:** The percentage of each row's total that falls into each column.\n\n**Calculation:** `(cell count ÷ row total) × 100`\n\n**When to use:** When you want to see how a specific group (row) distributes across different categories (columns).\n\n**Example:** If you're looking at \"Company vs Rating\" data:\n- Apple row: 36 people rated 1, 33 rated 2, etc.\n- Row percentage shows: \"Of all Apple respondents, 5.3% gave a rating of 1\"\n- All row percentages for Apple will add up to 100%\n\n### Column Percentage (Column B Percent) \n**What it shows:** The percentage of each column's total that comes from each row.\n\n**Calculation:** `(cell count ÷ column total) × 100`\n\n**When to use:** When you want to see how each category (column) is composed across different groups (rows).\n\n**Example:** In the same \"Company vs Rating\" data:\n- Rating \"1\" column: 36 from Apple, 25 from Google\n- Column percentage shows: \"Of all people who rated 1, 59.0% were Apple users\"\n- All column percentages for rating \"1\" will add up to 100%\n\n### Sample Percentage\n**What it shows:** The percentage of the entire sample that falls into each cell.\n\n**Calculation:** `(cell count ÷ total sample) × 100`\n\n**When to use:** When you want to see the overall distribution across your entire dataset.\n\n**Example:** In the same data:\n- Apple rating \"1\" cell: 36 people out of 2,371 total\n- Sample percentage shows: \"1.5% of all respondents were Apple users who rated 1\"\n- All sample percentages will add up to 100%\n\n## Visual Example\n\nHere's how the same data looks with different percentage types:\n\n| Company | Rating | Count | Row % | Column % | Sample % |\n|---------|--------|-------|-------|----------|----------|\n| Apple | 1 | 36 | 5.3% | 59.0% | 1.5% |\n| Apple | 2 | 33 | 4.8% | 51.6% | 1.4% |\n| Google | 1 | 25 | 1.5% | 41.0% | 1.1% |\n| Google | 2 | 31 | 1.8% | 48.4% | 1.3% |\n\n## When to Use Each Type\n\n### Use Row Percentages When:\n- **Comparing groups:** \"How do Apple users rate compared to Google users?\"\n- **Understanding group behavior:** \"What percentage of Apple users gave each rating?\"\n- **Identifying patterns within groups:** \"Do different companies have different rating distributions?\"\n\n### Use Column Percentages When:\n- **Understanding category composition:** \"Who makes up each rating level?\"\n- **Market share analysis:** \"What percentage of high ratings come from each company?\"\n- **Identifying dominance:** \"Which company dominates the low ratings?\"\n\n### Use Sample Percentages When:\n- **Overall distribution:** \"What's the general pattern across all respondents?\"\n- **Market sizing:** \"What percentage of the total market does each segment represent?\"\n- **Absolute impact:** \"How significant is each cell in the overall dataset?\"\n\n## Row and Column Totals\n\n### Row Totals\n- **Count:** Sum of all counts in the row\n- **Row %:** Always 100% (by definition)\n- **Column %:** Shows sample percentage (since column percentages don't sum meaningfully)\n- **Sample %:** Sum of sample percentages in the row\n\n### Column Totals \n- **Count:** Sum of all counts in the column\n- **Row %:** Shows sample percentage (since row percentages don't sum meaningfully)\n- **Column %:** Always 100% (by definition)\n- **Sample %:** Sum of sample percentages in the column\n\n## Three-Way Tables\n\nFor three-way tables (e.g., Company × Rating × Gender), the percentage calculations work the same way, but with additional complexity. You can create three-way tables by adding multiple pivots or by [grouping columns](grouping-columns) together.\n\n- **Row %:** Percentage within each company-gender combination\n- **Column %:** Percentage within each rating level\n- **Sample %:** Percentage of the entire sample\n\nThe totals follow the same logic as two-way tables, with row totals showing sample percentages for column percentages and vice versa.\n\n## Practical Tips\n\n- **Use row percentages** to compare groups\n- **Use column percentages** to understand category composition \n- **Use sample percentages** to see overall distribution\n- **Always show counts alongside percentages** for context\n\n## Weighting and Percentages\n\nWhen you apply a [weight column](../preparation/weighting) to your data, AddMaple automatically adjusts all percentage calculations to reflect the weighted sample.\n\n### How Weighting Affects Calculations\n\n**Weighted vs Unweighted:**\n- **Unweighted percentages:** Based on raw response counts\n- **Weighted percentages:** Based on weighted response counts that reflect your target population\n\n**Example with Weighting:**\n- Raw data: 100 Apple users, 200 Google users\n- Weighted data: 150 Apple users, 150 Google users (after applying demographic weights)\n- All percentages (row, column, sample) will be calculated using the weighted counts\n\n### Weighted Totals\n\nWhen weighting is active, you'll see both unweighted and weighted totals in the status line:\n- **Unweighted:** \"Showing 1,431 results from 870 rows\"\n- **Weighted:** \"Weighted: 1,520.5 results from 905.2 rows\"\n\nThe percentage calculations use the weighted totals, ensuring your analysis reflects the true population distribution.\n\n## Multiselect Questions and Rows vs Results\n\n[Multiselect questions](../data-types/multi-select) allow respondents to choose multiple options, which creates an important distinction between **rows** and **results**.\n\n### Understanding Rows vs Results\n\n**Rows (Respondents):**\n- Number of people who answered the question\n- Each person counts as one row, regardless of how many options they selected\n\n**Results (Answers):**\n- Total number of individual selections made\n- Each selected option counts as one result\n\n### Multiselect Example\n\nIf 100 people answer \"Which brands do you use?\" and can select multiple:\n- **50 people** select only \"Apple\"\n- **30 people** select both \"Apple\" and \"Google\" \n- **20 people** select only \"Google\"\n\n**Counts:**\n- **Rows:** 100 (number of respondents)\n- **Results:** 150 (50 + 60 + 20 individual selections)\n\n### How This Affects Percentages\n\n**Row Percentages (Column A Percent):**\n- Based on the number of respondents in each row\n- \"Of all Apple users, what percentage selected each option?\"\n\n**Column Percentages (Column B Percent):**\n- Based on the total number of times each option was selected\n- \"Of all 'Apple' selections, what percentage came from each user group?\"\n\n**Sample Percentages (Sample Percent):**\n- Based on the total number of selections across all respondents\n- \"What percentage of all selections were 'Apple' from each group?\"\n\n### Status Line with Multiselect\n\nThe status line shows both counts:\n```\nShowing 1,431 results from 870 rows\n```\n\nThis tells you:\n- 870 people answered the question (rows)\n- They made 1,431 total selections (results)\n- Results exceed rows because people could select multiple options\n\n### Hiding Multiselect Data\n\nWhen you [hide categories](filtering-vs-hiding) in multiselect data:\n- **Empty-like categories** (EMPTY, \".\") hide entire rows\n- **Other categories** only hide the matching results, not the rows\n\nExample status line:\n```\nShowing 1,411 results from 870 rows\n20 results hidden\n• None of the above — 20 results\n```\n\nThis means 20 individual selections were hidden, but the 870 respondents still count toward the row base.\n\n## Key Points\n\n- Row percentages show how each group distributes across categories\n- Column percentages show how each category is composed across groups\n- Sample percentages show the overall distribution in your dataset\n- Each percentage type answers a different research question\n- In charts, use the Percentage Base control to select which percentage to display\n- Hover over any cell to see all three percentage types in the tooltip\n- In tables, customize which percentage columns are visible\n- Row and column totals use sample percentages when the other percentage type doesn't sum meaningfully\n- Choose your percentage type based on what you want to learn from your data\n- Weighting adjusts all calculations to reflect your target population\n- Multiselect questions create a distinction between respondents (rows) and individual selections (results)\n- Understanding rows vs results is crucial for interpreting multiselect data correctly\n\n"},"pivot-chart-and-table/time-charts":{"title":"Time Charts","category":"Pivot Chart and Table","slug":"pivot-chart-and-table/time-charts","blurb":"Visualize data trends over time with interactive column and line charts. Explore temporal patterns with flexible view options.","order":7,"filename":"time-charts.md","uid":"pivot-chart-and-table/time-charts","content":"\n# Time Charts\n\nTime charts help you visualize how data changes over time. AddMaple provides flexible time visualizations that let you explore temporal patterns with both column and line chart views, making it easy to spot trends and seasonal variations in your data.\n\n## When to Use Time Charts\n\nTime charts are ideal for:\n\n- **Trend analysis** — See how values change across time periods\n- **Seasonal patterns** — Identify recurring patterns or cycles in your data\n- **Comparative time series** — Compare trends across different categories\n- **Period-over-period analysis** — Understand growth or decline over specific timeframes\n- **Temporal exploration** — Interactively explore data at different time scales\n\n## Creating a Time Chart\n\nTo create a time chart in AddMaple:\n\n1. **Select a date column** — Choose the date column as your primary pivot\n2. **Optional: Add a category** — Add a second column (like product type, region, or sentiment) to compare multiple series\n3. **View your chart** — AddMaple automatically generates a time chart\n\n### Single Date Column\n\nWhen you pivot by a date column alone, you get a simple time chart showing values at each time point.\n\n**What you see:**\n- X-axis: Time periods (automatically formatted based on your date granularity)\n- Y-axis: Count or aggregated values\n- Interactive bars showing data for each time period\n\n### Date + Category\n\nWhen you pivot by a date column and a category column, you get a multi-series time chart with one line or group of bars per category.\n\n**Example scenarios:**\n- Review dates + sentiment (Positive, Neutral, Negative)\n- Sales dates + product type (Widget A, Widget B, Widget C)\n- Event dates + region (North, South, East, West)\n\n## Chart View Modes\n\nTime charts support two complementary visualization modes that you can toggle between:\n\n### Column View (Default)\n\nShows data as vertical bars, one bar per time period.\n\n**Best for:**\n- Comparing magnitudes easily at a glance\n- Seeing exact heights and proportions\n- Traditional time series analysis\n- Reports and presentations\n\n**Features:**\n- Single-series charts show bars in the chart's color\n- Multi-series charts use grouped or stacked bars by default\n- Hover over bars to see exact values\n- Easy to sort and filter data\n\n### Line View\n\nShows data as connected lines that trace trends across time.\n\n**Best for:**\n- Clearly seeing trends and direction of change\n- Reducing visual clutter with many time periods\n- Emphasizing continuity and flow\n- Comparing trends across multiple series\n\n**Features:**\n- Each series gets its own color-coded line\n- Points on the line show actual data values\n- Hover over points to see detailed information\n- Smooth rendering even with many time periods\n- Points remain visible and interactive\n\n### Switching Between Views\n\nTo switch between column and line views:\n\n1. **Look for the view toggle** — Located in the chart controls (top right of the chart)\n2. **Select your preferred view** — Choose \"Columns\" or \"Line\"\n3. **Chart updates instantly** — Data and interactions remain the same\n\nThe toggle remembers your preference while working with that chart.\n\n## Controls and Options\n\nTime charts support the same filtering and display controls as other pivots:\n\n### Aggregation by Another Column\n\nInstead of counting records at each time point, you can aggregate values from a numeric column:\n\n1. **Click the aggregation control** — Look for \"Number of records\" or similar in the sentence bar\n2. **Choose an aggregation type:**\n - **Total** — Sum all values in your numeric column (e.g., total revenue per day)\n - **Average** — Calculate the mean of your numeric column (e.g., average order value over time)\n - **Median** — Find the median value (e.g., median salary across time periods)\n - **Count Unique** — Count distinct values from a categorical column (e.g., unique customers per day)\n3. **Select your aggregation column** — Choose which numeric or categorical column to aggregate\n4. **Visualize aggregated data** — Your time chart now shows the aggregated values instead of counts\n\n**Examples:**\n- Total revenue by week (sum of sales amounts)\n- Average temperature by month (mean of daily temperatures)\n- Median response time by date (median of processing times)\n- Unique users per day (count distinct user IDs)\n\nThis works seamlessly in both column and line view modes.\n\n### Count vs Percentage\n\nWhen you have multiple categories:\n\n1. **Select \"Percentage\"** — Shows each category as a percentage of the total for that time period\n2. **Visualize proportions** — See relative contributions at each point in time\n3. **Compare compositions** — Understand how the mix changes over time\n\n### Sorting\n\nOrganize your data in meaningful ways:\n\n- **Sort by time** — Standard chronological ordering (default)\n- **Sort by value** — Rank time periods by total or specific category values\n- **Sort ascending/descending** — Control the sort direction\n\n### Filtering\n\nFocus on specific time periods or categories:\n\n- **Filter by date range** — Select specific start and end dates\n- **Filter by category** — Show or hide specific categories in multi-series charts\n- **Use exclude filters** — Hide unwanted categories while showing the rest\n\n## Multi-Series Time Charts\n\nWhen you add a category column, you create multi-series time charts that show how different groups evolved over time.\n\n### Single Series (Date Only)\n\nOne line or bar group showing overall trends:\n- Simple and clear\n- Good for focused analysis\n- Minimal visual complexity\n\n### Multiple Series (Date + Category)\n\nMultiple lines or bar groups, one per category:\n- Compare trends across categories\n- See which categories drive overall patterns\n- Identify leaders and laggards\n\n**Example:**\nAnalyze quarterly revenue by product line:\n- Each line represents a product\n- X-axis shows quarters over time\n- Y-axis shows revenue\n- Easy to see which products are growing\n\n## Interactive Features\n\n### Hover Information\n\nHovering over data points shows detailed information:\n\n- **Exact value** — Precise count or aggregated number\n- **Date/time period** — Which time point this represents\n- **Category** — Which category or series (for multi-series charts)\n- **Percentage** — Percentage of total (if percentage mode is active)\n\n### Click to Filter\n\nIn column view, click on a bar to filter to that time period, helping you drill deeper into specific dates or ranges.\n\n### Responsive Layout\n\nTime charts automatically adjust to fit your screen:\n\n- **Desktop** — Full-width display with legend on the right\n- **Mobile** — Optimized layout for smaller screens\n- **Dashboard** — Stretches to fill the grid item height\n\n## Best Practices\n\n### Choosing a View Mode\n\n- **Use columns** for reports, presentations, and when precise value comparison matters most\n- **Use lines** for trend analysis, multi-series comparison, and when you have many time periods\n- **Switch between views** to find the perspective that best reveals your story\n\n### Formatting Time Data\n\nFor best results with time charts:\n\n- **Use standard date formats** — AddMaple recognizes common formats like YYYY-MM-DD, MM/DD/YYYY\n- **Consistent date columns** — All dates in the column should use the same format\n- **Include complete dates** — Even if you only care about months, include the full date with day\n\n### Multi-Series Analysis\n\nWhen comparing multiple categories:\n\n- **Limit categories** — Too many lines become cluttered; consider filtering to key groups\n- **Use contrasting colors** — AddMaple's color scheme makes different series easy to distinguish\n- **Switch to line view** — Clearer with many series or long time ranges\n\n### Effective Storytelling\n\n- **Highlight anomalies** — Use filtering to focus on interesting patterns\n- **Compare time periods** — Use filtering to show before/after scenarios\n- **Export for reports** — Save interesting views as charts in your reports\n\n## Data Granularity\n\nTime charts automatically adapt to your date granularity:\n\n- **Days** — Good for short-term trends (days to weeks)\n- **Weeks** — Balance between detail and overview\n- **Months** — Standard for quarterly and yearly planning\n- **Quarters** — Useful for business analysis\n- **Years** — Long-term trend analysis\n\nAddMaple intelligently formats dates based on how many unique dates you have and the date range covered.\n\n## Troubleshooting\n\n### Chart Not Appearing\n\n- **Verify date column** — Ensure you've selected a date type column as your pivot\n- **Check data validity** — Make sure the column contains valid dates\n- **Look for errors** — Review any error messages about date formatting\n\n### Too Many Time Periods\n\n- **Switch to line view** — Better for handling many time periods\n- **Filter date range** — Focus on a specific time window\n- **Aggregate to wider periods** — Group into months or quarters if working with daily data\n\n### Multi-Series Not Showing\n\n- **Verify second column** — Confirm you've added a category column for series\n- **Check visibility** — Ensure categories aren't filtered out\n- **Look for data** — Verify that category combinations have data for each time period\n\n### Legend Not Showing\n\n- **Check screen size** — Small screens may hide legend initially; expand your view\n- **Look in chart settings** — Verify the legend hasn't been explicitly hidden\n- **Use hover** — Hover over points to see which series they represent\n\n## Key Points\n\n- Time charts visualize data changes across time with automatic date formatting\n- Create simple time charts with just a date column\n- Create multi-series charts by adding a category column (like sentiment or region)\n- Choose between column view (great for value comparison) and line view (excellent for trends)\n- Toggle between views to find the best perspective for your analysis\n- All standard filters, sorting, and percentage controls work with time charts\n- Interactive tooltips provide detailed information on hover\n- Time charts automatically adapt to different screen sizes and time granularities\n- Use columns for reports and presentations; use lines for trend analysis\n\n---\n\n### Key takeaways\n\n- Time charts require a date column and optionally a category column for multi-series analysis\n- Two view modes (column and line) provide different perspectives on the same data\n- Column view excels at precise value comparison; line view excels at showing trends\n- Switch between views to find the best visualization for your analysis\n- All filtering, sorting, and percentage controls work seamlessly with time charts\n- Interactive features let you explore data by hovering and filtering on time periods\n- Multi-series time charts compare trends across different categories\n- Use line view for many time periods to reduce visual clutter\n- Consider your audience and analysis goals when choosing between view modes\n\n---\n\n"},"preparation/colors":{"title":"How to apply color presets to all charts via Settings","category":"Preparation","slug":"preparation/colors","blurb":"Set chart colors using your own color schemes or presets to enable All subsequent charts and visualizations to reflect your chosen colors while you explore","order":2,"filename":"colors.md","uid":"preparation/colors","content":"# How to change project color presets\n\nBy default, all charts in AddMaple use our **standard AddMaple color palette**. \nYou can customize colors in two different ways, depending on whether you want to update them **across the whole project** or **lock in colors for specific variables**.\n\n## 1. Project-Wide Color Changes (Global)\n\n**What it does**: Updates the default color palette across the **entire project**, so all chart types automatically use your chosen colors.\n\n**When to use it**: \n- You want to apply your **brand colors** consistently across every chart and data type. \n- You want all visualizations to follow a **single unified palette**. \n\n**How to do it**: Go to **Settings → Project Settings**, and select a preset or define your own 'custom' palette, to update the project color settings. See detailed steps below. \n\n> NOTE: After updating, every chart in the project (bar charts, maps, word clouds, dot plots, box plots, stacked pivot charts, etc.) will reflect the new palette.\n\n## 2. Column-Specific Color Assignments (Locked to a variable or specific categories in a chart)\n\n**What it does**: Assigns fixed colors to specific variables so they are **always represented consistently**, no matter which chart they appear in. If you're viewing two columns, make sure the chart with the set colors is in the legend's side on the right. Then you'll see the colors reflected, even when viewing this column by another one. \n\n**When to use it**: \n- You want **Segment A** to always appear pink, **Segment B** always blue, etc. \n- You are comparing charts side by side and need colors to remain stable for clarity. \n\n**How to do it**: See [Managing individual column colors](../legend/legend). \n\n> Note: Once you have locked colors in for a variable, they remain the same across all charts, even if the global palette changes. If you pivot that variable with another one, make sure the color-specific variable is on the right side, with those color-locked categories under the legend, to see the colors when pivoting two or more charts. If you're viewing a sentiment scale view, the sentiment colors will be visible though.\n\n### Recap\n\n**Project-wide changes** = update the overall theme/palette for **all charts** in your project. \n**Column-specific changes** = lock in consistent colors for **particular variables** (segments, categories, etc.), making comparisons easier and more reliable.\n\n## How to set Project-Wide Colors\n\nThere are two ways to adjust project-wide colors: **using a preset** or **defining a custom palette**.\n\n### Option 1: Switch Preset\n\n**What it does**: Applies one of AddMaple’s built-in presets across the project. \n**When to use it**: If you want ready-made palettes where categorical, numeric, sentiment, word cloud, and other chart types are already tuned to work correctly. \n**How to do it**: \n 1. From the **Explore Dashboard**, open **More menu → Settings → Project Settings**. \n 2. Under **Colors**, select a preset. \n 3. Click **Save** (bottom right). \n\nAll charts in the project will update (except those with locked column-specific colors). PowerPoint exports will also follow the chosen preset. \n\n\n*Select a color preset from the Project Settings menu to apply it across all charts in your project.*\n\n### Option 2: Create a Custom Palette\n\nIf you select **Custom**, you’ll see **three configuration** sections that you need to pay attention to: \n\n#### 1. Define Category Colors\n- Used for categorical data (multiple choice and other categories, etc.). \n- Add **8 or more colors** to give us a broad palette for charts such as word clouds, bar charts, stacked bar charts, etc. \n- If a column contains more categories than the colors provided, we will use the settings below to determine appropriate colors: \n - **Interpolate (Recommended)** (stretches colors across all categories)\n - **Repeat** (cycles through your palette and repeats colors where the categories in a column exceed the palette options you provided in the custom settings). \n\n\n*Configure category colors for categorical data like multiple choice questions, with options to interpolate or repeat colors for additional categories.*\n\n#### 2. Define Sentiment Colors\n\n- Used for ordered scales (e.g., Likert, satisfaction, sentiment, ranking). \n- Define **most negative, neutral, and most positive ranges**. \n- Add darkest shades for the strongest ends of the scale. \n - Example: If using green for positive → darkest green = most positive. \n - If using red for negative → darkest red = most negative. \n> Tip: Even on an **11-point scale**, AddMaple auto-generates intermediate colors accordingly. You only need to specify the most negative and most positive color choice.\n\n\n*Set up sentiment colors for ordered scales like Likert ratings, defining the most negative, neutral, and most positive color ranges.* \n\n#### 3. Define Numeric Scale Colors\n\n- Used for numbers and map visualizations. \n- Add **3 colors**: \n - **Light Color** → auto-allocated to smallest counts (lowest values) \n - **Middle Grey Color** → auto-allocated average counts (mid-range values) \n - **Dark Color** → auto-allocated to largest counts (highest values) \n\n\n*Configure numeric scale colors for maps and numeric visualizations, with light colors for low values and dark colors for high values.*\n\n**What we mean by counts**: \"Counts\" are simply the number of people or responses that fall into a particular category, range, or location. \n\nSometimes you need to distinguish between larger and smaller numbers, for example: \n- If you’re showing a map of survey respondents by state, a state with **fewer respondents** will be shaded in the lightest color. \n- A state with a **lower number of respondents** will use the light color. \n- A state with the **highest number of respondents** will be shaded darkest.\n- If you show average salaries by state, the shading of the states will reflect comparative average salaries, with low salary averages reflected by light shades and higher salary ranges shown with darker shades of color. \n\nWhen you set the color settings correctly, darker shades will quickly help you see where 'more responses' lie, or 'bigger values' sit on your map or other visualizations. In essence: the darker the color, the bigger the number, value or count.\n\n\n*Use color theory principles to find complementary colors that work well together for your custom palette.*\n\n\n*Compare how the same dashboard looks with default AddMaple colors versus your custom color palette.*\n\nPreviews below the editor show how your chosen palette looks, distinguishing how the three configuration settings will be interpreted, Category Colors, Sentiment Colors and Numeric Scale Colors. Once satisfied, click **Save** on the bottom left of the modal, to apply it. \n\n---\n\n## Quick Summary\n\n- **Presets** → Fast, built-in palettes tuned for all configuration settings and chart types. \n- **Custom palette** → Full control; need to define brand colors for categories, sentiment, and numeric data. \n\n\n*Compare how segment-specific color assignments look compared to default project colors in the same chart.*\n\n👉 For chart-specific exceptions, you can override project-level colors in the chart's **legend tab**. Learn more: [Managing individual column colors](../legend/legend).\n"},"preparation/combining-columns":{"title":"How to combine columns","category":"Preparation","slug":"preparation/combining-columns","blurb":"Learn how to combine multiple columns into a single variable when survey exports split data across columns.","order":3,"filename":"combining-columns.md","uid":"preparation/combining-columns","content":"# How to combine columns\n\nSometimes survey exports split a single variable across multiple raw columns. For example, a multi-select question such as \"Which colors do you like?\" might export into three separate columns: **Red**, **Yellow**, **Green**. Each row then shows values like `1 | 0 | 1` or `Red | | Green`. \n\nIn these cases, you can use **Combine Columns** to merge them back into one variable. This is especially useful for [multi-select questions](../data-types/multi-select) that have been split across multiple columns. \n\n\n\n---\n\n### Where to find it\n\nOpen [Manage Column(s)](manage-columns). The interface has three parts: \n- On the **left**, a searchable list of all raw columns \n- On the **right**, a details pane showing the selected column (or combined/grouped column) \n- At the **bottom right**, a **Save** button to confirm changes \n\n---\n\n### How to combine\n\n1. In the list of columns (left panel), click the first column you want to include. \n2. Hold **Shift** and select additional columns. You can also select a continuous range this way. \n3. The right-hand details pane will update with a new screen and a **Combine Columns** button. \n - If the columns cannot be combined, an error message will explain why. \n\n \n\n---\n\n### Confirming values\n\n- If each column contains a single value (e.g. \"Red\", \"Yellow\", \"Green\"), AddMaple will combine them immediately. \n- This also includes CATA-style exports where each selected column mostly contains blanks, and the only non-empty value per column is that column’s label (e.g. one column per option). In these cases, AddMaple combines without prompting.\n- If columns contain two values (e.g. \"checked/unchecked\", `1/0`, \"Yes/No\"), you'll be asked to confirm which value should be treated as **positive** and which as **negative**. \n\n \n\n---\n\n### After combining\n\n- You'll see a new **Combined Column details view** in the right pane. It looks like a standard column view, but at the bottom it shows the source columns that were merged. \n- In the column list (left panel), the raw columns will collapse into a single combined column. A **chevron** indicates you can expand to see the underlying source columns. \n\n \n\n---\n\n### Saving and editing\n\n- Click **Save** in the bottom right for your changes to take effect. \n- Columns that are not compatible cannot be combined — the option will be blocked. \n\n---\n\n### Separating columns\n\nSeparating is not only for undoing a manual combine. Sometimes AddMaple will automatically combine raw columns when it detects a multi-select or single-select question spread across multiple columns. If you prefer to work with those columns individually, you can separate them. \n\nTo separate: \n\n1. Open the combined column in the details pane. \n2. Click the **Separate** button in the top right. \n3. The combined variable will be removed, and the raw source columns will reappear as individual variables in the column list. \n\nYou can combine them again later if needed. \n\n \n\n**Example:** \n\nA survey platform may export Q10a, Q10b, Q10c as separate columns for a grid of product features. AddMaple might automatically combine these into one multi-select question. If you prefer to analyze each feature separately, use **Separate** to break them back into individual variables. \n\n---\n\n### Example\n\nA survey export contains three columns: **Red**, **Yellow**, **Green**. Each row has either `1` or `0` in each column. \n- Select the three columns and click **Combine Columns**. \n- Confirm that `1` is **positive** and `0` is **negative**. \n- The result is one multi-select variable called \"Colors liked,\" which behaves consistently in charts and exports. \n\n---\n\n### Key points\n\n- Combining is useful for reconstructing single variables split across multiple columns. \n- Separating lets you break apart either manual or automatic combines. \n- The raw data is never modified. \n- All changes apply across your project, including exports. \n\n---\n"},"preparation/date-binning":{"title":"Date Binning","category":"Preparation","slug":"preparation/date-binning","blurb":"Learn how to configure how date and datetime columns are grouped into bins for analysis and visualization.","order":6,"filename":"date-binning.md","uid":"preparation/date-binning","content":"# Date Binning\n\nDate binning allows you to group date and datetime values into meaningful time periods for analysis. Instead of analyzing individual dates, you can group them into weeks, months, quarters, or custom time ranges.\n\n---\n\n## Accessing Date Binning Settings\n\nYou can configure date binning in two ways:\n\n### Method 1: Column Settings (Recommended)\n1. **Click on the column header** of a date or datetime column\n2. **Select \"Column Settings\"** from the dropdown menu\n3. **Scroll to the \"Binning\" section**\n\n### Method 2: Manage Columns\n1. **More → Project Settings** from the dashboard\n2. **Select your date column**\n3. **Scroll to the \"Binning\" section**\n\n---\n\n## Binning Options\n\n### Auto (Recommended)\nAutomatically creates optimal time-based bins across your date range. You can adjust the number of bins using the slider.\n\n**Best for:** Most use cases where you want balanced time periods\n**Example:** A dataset spanning 2 years might be binned into 8-12 periods\n\n### Calendar Periods\nGroups dates by natural calendar boundaries:\n\n- **Year**: Groups by calendar year (2023, 2024, etc.)\n- **Quarter**: Groups by quarters (Q1 2023, Q2 2023, etc.)\n- **Month**: Groups by calendar months (Jan 2023, Feb 2023, etc.)\n- **Week**: Groups by calendar weeks (Monday to Sunday)\n- **Day**: Groups by individual days\n- **Hour**: Groups by hour of day\n\n**Best for:** When you need standard business reporting periods\n**Example:** Monthly sales reports, quarterly business reviews\n\n### Fixed Intervals\nCreates bins of fixed duration that you define:\n\n- **Every X minutes**: For high-frequency data\n- **Every X hours**: For daily patterns\n- **Every X days**: For custom weekly patterns\n- **Every X weeks**: For bi-weekly or monthly patterns\n\n**Best for:** When you need consistent time intervals regardless of calendar boundaries\n**Example:** Every 7 days starting from a specific date\n\n### Custom Breakpoints\nDefine your own date/time boundaries manually. You can set specific dates and times as breakpoints.\n\n**Best for:** When you need specific time periods (e.g., before/after an event)\n**Example:** Pre-launch vs. post-launch periods\n\n---\n\n## Live Preview\n\nThe binning interface shows a **live timeline preview** so you can see exactly how your data will be grouped before applying changes. This helps you:\n\n- Verify the number of bins created\n- Check that time periods make sense for your data\n- See the distribution of values across bins\n- Adjust settings until you're satisfied\n\n---\n\n## Examples\n\n### Example 1: Monthly Sales Analysis\n**Scenario:** You have daily sales data and want monthly summaries\n**Solution:** Use Calendar Periods with Month grain\n**Result:** Each month becomes a single bin (Jan 2023, Feb 2023, etc.)\n\n### Example 2: Weekly User Activity\n**Scenario:** You want to analyze user behavior in 7-day periods\n**Solution:** Use Fixed Intervals with \"Every 7 days\"\n**Result:** Consistent weekly bins regardless of calendar weeks\n\n### Example 3: Before/After Campaign Analysis\n**Scenario:** You want to compare data before and after a marketing campaign launch\n**Solution:** Use Custom Breakpoints with the campaign launch date\n**Result:** Two bins: \"Before Campaign\" and \"After Campaign\"\n\n---\n\n## Tips for Date Binning\n\n### Choose the Right Grain\n- **Year**: For long-term trends and annual comparisons\n- **Quarter**: For business reporting and seasonal analysis\n- **Month**: For monthly business cycles and seasonal patterns\n- **Week**: For weekly patterns and short-term trends\n- **Day**: For daily patterns and weekday vs. weekend analysis\n- **Hour**: For intraday patterns and time-of-day analysis\n\n### Consider Your Data Range\n- **Short periods** (days/weeks): Use smaller grains (day, hour)\n- **Medium periods** (months/years): Use medium grains (week, month)\n- **Long periods** (years/decades): Use larger grains (quarter, year)\n\n### Handle Time Zones\n- Fixed intervals can be aligned to UTC boundaries for consistency\n- Calendar periods respect local time zones\n- Consider your audience's time zone when choosing settings\n\n---\n\n## Common Use Cases\n\n### Business Reporting\n- **Monthly reports**: Calendar Periods → Month\n- **Quarterly reviews**: Calendar Periods → Quarter\n- **Annual summaries**: Calendar Periods → Year\n\n### User Behavior Analysis\n- **Weekly patterns**: Fixed Intervals → Every 7 days\n- **Daily patterns**: Calendar Periods → Day\n- **Hourly patterns**: Calendar Periods → Hour\n\n### Event Analysis\n- **Before/after events**: Custom Breakpoints\n- **Campaign periods**: Custom Breakpoints\n- **Seasonal analysis**: Calendar Periods → Month or Quarter\n\n---\n\n## Troubleshooting\n\n**My bins are too granular/fine**\n- Try a larger time grain (e.g., change from Day to Week)\n- Reduce the number of bins in Auto mode\n\n**My bins are too broad**\n- Try a smaller time grain (e.g., change from Month to Week)\n- Increase the number of bins in Auto mode\n\n**Some bins are empty**\n- This is normal for sparse data\n- Consider using Auto mode for better distribution\n- Check if your date range is appropriate for the grain\n\n**Dates look wrong**\n- Ensure your column is detected as Date/Datetime type\n- Check the date format in your source data\n- Use Manage Columns to change the column type if needed\n"},"preparation/group":{"title":"Group Data","category":"Preparation","slug":"preparation/group","blurb":"Learn how to group and organize your data in AddMaple.","order":4,"filename":"group.md","uid":"preparation/group","content":"# How to group columns\n\nSurvey platforms often export grid or matrix questions as separate columns. For example, a set of opinion questions might appear as **Q5a: \"Service was friendly\"**, **Q5b: \"Product was reliable\"**, **Q5c: \"Value for money\"**. \n\nAddMaple often detects these automatically and creates a **group**, so you can view and analyze them together. If not, you can manually group or ungroup columns in [Manage Column(s)](manage-columns). \n\n\n\n---\n\n### Where to find it\n\nOpen **Manage Column(s)**. The interface has three parts: \n- On the **left**, a searchable list of all raw columns \n- On the **right**, a details pane showing the selected column or group \n- At the **bottom right**, a **Save** button to confirm changes \n\nGrouped columns appear collapsed under a single title in the left panel, with a **chevron** to expand and view the underlying columns. \n\n \n\n---\n\n### How to group\n\n1. In the list of columns (left panel), click the first column you want to include. \n2. Hold **Shift** and select additional columns. \n3. The right-hand details pane will update with a new screen and a **Group X Items** button (where X is the number of columns selected). \n4. Click **Group X Items**. \n\n \n\n---\n\n### Group details\n\nAfter grouping, the details pane will show a **Group details view**. Here you can: \n- Edit the **group title** (the name shown when the group is used in charts). \n- For each column inside the group, view and edit: \n - **Display Name (in this group)** – the name that appears in legends, tables, and exports \n - **Original Column Name** – the raw survey export name \n\nAddMaple intelligently suggests both the group name and display names by detecting patterns in the selected column names. These can be adjusted at any time. \n\n \n\n---\n\n### Ungrouping columns\n\nSometimes AddMaple may automatically group columns, but you prefer to analyze them separately. To ungroup: \n1. Open the grouped variable in the details pane. \n2. Click the **Ungroup** button in the top right. \n3. The group will be removed and the raw columns will appear individually in the list. \n\n \n\n---\n\n### Example\n\nA survey exports four Likert questions (Q5a–Q5d). AddMaple detects them as a group called **Q5: Opinions on service**. \n- In the **Group details view**, you rename the group to **Service evaluation**. \n- For each item, you see the **Display Name** (e.g. \"Friendly staff\") alongside the **Original Column Name** (e.g. Q5a). \n- AddMaple suggested these display names automatically based on the column naming pattern, but you adjust them for clarity. \n- In charts and exports, the group appears as a clean set of labeled items instead of raw codes. \n\n---\n\n### Key points\n\n- Groups are useful for matrix or grid questions with consistent scales. You can also [group columns from the pivot chart view](../pivot-chart-and-table/grouping-columns) for more dynamic grouping. \n- AddMaple suggests group and item names based on column patterns, but you can edit them. \n- You can always group or ungroup manually. \n- The raw data is never modified. \n\n---\n"},"preparation/header-rows":{"title":"Header Rows","category":"Preparation","slug":"preparation/header-rows","blurb":"Configure how many header rows AddMaple reads from your data file to ensure column names are correctly detected.","order":8,"filename":"header-rows.md","uid":"preparation/header-rows","content":"\n# How to configure header rows\n\nSome survey exports include multiple header rows. For example, the first row might contain question codes (like `Q5_satisfaction`), while the second row contains the full question text (like \"How satisfied are you with our service?\"). AddMaple automatically detects these multi-row headers, but you can override this setting if needed.\n\n**Configure header rows in Project Settings** to control how many top rows are treated as column headers. This ensures your data is imported correctly and preserves important metadata from additional header rows.\n\n---\n\n## When to use this feature\n\nYou should adjust header rows when:\n\n- **Survey exports have descriptive second rows** — Platforms like SurveyMonkey or Qualtrics often include question text in a second header row\n- **Auto-detection is incorrect** — AddMaple might miss multi-row headers or incorrectly treat data rows as headers\n- **You want to preserve both labels** — Keep both the technical column name and the human-readable description\n\n---\n\n## Accessing header row settings\n\n1. **More → Settings** from the dashboard\n2. **Select the \"Manage Project\" tab**\n3. **Scroll to the \"Header rows\" section**\n\nYou'll see a dropdown showing the current number of header rows (1–5).\n\n---\n\n## How header rows work\n\n### Single header row (default)\nWhen set to **1 header row**, AddMaple treats only the first row as column names:\n- **Row 1**: `participant_id, age, satisfaction`\n- **Row 2**: Data starts here\n\n**Result**: Columns named `participant_id`, `age`, `satisfaction`\n\n### Multiple header rows\nWhen set to **2 header rows**, AddMaple combines both rows into descriptive column names:\n- **Row 1**: `q5_ease, q5_value, q5_support`\n- **Row 2**: `Ease of use, Value for money, Customer support`\n\n**Result**: Columns named `q5_ease - Ease of use`, `q5_value - Value for money`, `q5_support - Customer support`\n\nThe original technical name (Row 1) is preserved in the column metadata so you can reference it if needed.\n\n---\n\n## Changing header rows\n\nWhen you change the header row count:\n\n1. **Select a new value** from the dropdown (1–5)\n2. **A confirmation dialog will appear** with the message: \"Changing this will remove any project configuration and reload the project\"\n3. **Click \"Apply and Reload\"** to confirm\n4. **AddMaple will**:\n - Save the new header row count\n - Clear existing column configuration (names, types, groups, merges)\n - Reload the project with the new setting\n\n\n---\n\n## Examples\n\n### Example 1: Survey with descriptive headers\nYour survey export has:\n- **Row 1**: Question codes (`screener_2_market_r`, `screener_2_ux_research`)\n- **Row 2**: Full text (`Market research`, `User, UX, product, design, or HCI research`)\n\n**Solution**: Set header rows to **2**\n**Result**: Columns display both the code and description: `screener_2_market_r - Market research`\n\n### Example 2: Simple CSV with one header\nYour data file has:\n- **Row 1**: `Name, Email, Age, Country`\n- **Row 2**: Data starts here\n\n**Solution**: Keep header rows at **1**\n**Result**: Columns named exactly as shown in Row 1\n\n### Example 3: Incorrectly detected headers\nAddMaple mistakenly treated your first data row as a second header:\n- **Row 1**: Headers\n- **Row 2**: Data (but was treated as a second header)\n\n**Solution**: Change header rows from **2** to **1**\n**Result**: Row 2 is now treated as data, and you don't lose any responses\n\n---\n\n\n## How to tell if header rows are wrong\n\nIf header rows are incorrectly configured, you'll see symptoms in your charts and dashboard:\n\n### Too few header rows (e.g., set to 1 when file has 2)\n- **Dashboard shows extra columns** with generic names like \"Row 2: Options (matrix, checkbox)\"\n- **Charts include header text as data** — You'll see descriptive labels appearing as data points in your visualizations\n- **Row counts are off by one** — Your dataset appears to have one extra row\n- **Column names are technical codes** instead of human-readable labels\n\n### Too many header rows (e.g., set to 2 when file has 1)\n- **First data row is missing** — Your actual first respondent's data is treated as a second header\n- **Row count is one less** than expected\n- **Columns may have strange combined names** if the first data row was merged with the real header\n- **Values in charts don't match** your source data\n\n**Visual check**: Open a simple chart or the data table. If you see text that should be a column name appearing as data (or vice versa), adjust your header row setting.\n\n---\n\n## Troubleshooting\n\n**My column names look wrong**\n- Check if your file has multiple header rows\n- Increase header rows to **2** if you see descriptive text in the second row\n- Decrease to **1** if data is being treated as headers\n\n**I see header text appearing in my charts**\n- Your header rows setting is too low\n- Increase by 1 and reload to treat those rows as headers instead of data\n\n**I'm missing my first data row**\n- Your header rows setting is too high\n- Decrease by 1 and reload to treat that row as data instead of a header\n\n**I lost my column configuration**\n- Changing header rows clears configuration by design\n- You'll need to reconfigure columns after the reload\n- Calculated columns are preserved\n\n**The confirmation appears every time**\n- This is expected when changing from the saved value\n- Once saved and reloaded, the new value becomes the baseline\n\n**Second row information is missing**\n- Ensure header rows is set to **2** or higher\n- Check that your source file actually has a second header row with content\n- Combined names will include both rows separated by ` - `\n\n---\n\n### Key points\n- Header row detection is usually automatic\n- Override when survey exports include multiple descriptive rows\n- Changing this setting clears column configuration but preserves calculated columns\n- Multi-row headers are combined into readable column names with preserved metadata\n\n---\n\n"},"preparation/importing-and-preparing-data":{"title":"Importing and Preparing Data in AddMaple","category":"Preparation","slug":"preparation/importing-and-preparing-data","blurb":"Learn how AddMaple automatically detects and prepares your data, including column types, merging, and grouping.","order":1,"filename":"importing-and-preparing-data.md","uid":"preparation/importing-and-preparing-data","content":"# Importing and Preparing Data in AddMaple\n\nThis article explains what happens when you load a dataset in AddMaple, how the app detects and tidies columns, and how to review or change those decisions.\n\n---\n\n## Supported file types\n\n- **CSV**\n- **Excel** (`.xlsx`, `.xls`)\n- **SPSS** (`.sav`)\n- Exports from most survey tools (e.g., Qualtrics, SurveyMonkey, Typeform, Google Forms)\n\nNo reformatting is required before upload.\n\n---\n\n## What AddMaple does on upload\n\n1. **Scans headers** and a sample of values.\n2. **Assigns a column type**:\n - *Numeric* (e.g., Likert 1–5, counts, percentages)\n - *Categorical (single-select)*\n - *Multi-select (checkbox sets)*\n - *Text / open-ended*\n - *Date/Datetime*\n - *Boolean* (Yes/No, True/False, 1/0)\n3. **Merges** columns that belong to one question but were exported as many columns (common for single-selects and multi-selects).\n4. **Groups** related columns that share the same stem and scale (Likert/grid questions).\n5. **Generates readable names** for merged and grouped items by removing repeated stem/answer text often embedded in headers.\n\nAll steps are editable in **Manage columns**.\n\n---\n\n## Merging columns (single-select and multi-select)\n\nMany survey exports use **one column per answer option**. AddMaple collapses those into a single column so you analyze one variable instead of hunting across many.\n\n### Example: single-select exported as multiple dichotomies \n*Question:* \"What is your favorite color?\"\n\n**Raw export (one column per option, with 1/0 flags):**\n\n- **Respondent 1**: Red=1, Yellow=0, Green=0, Blue=0\n- **Respondent 2**: Red=0, Yellow=1, Green=0, Blue=0\n- **Respondent 3**: Red=0, Yellow=0, Green=1, Blue=0\n\n**After merge in AddMaple (one categorical column):**\n\n- **Respondent 1**: Red\n- **Respondent 2**: Yellow\n- **Respondent 3**: Green\n\n### Example: multi-select (checkbox) exported as many columns \n*Question:* \"Select up to three colors you like.\"\n\n**Raw export (one column per option, 1/0 or Yes/No):**\n\n- **Respondent 1**: Red=1, Yellow=0, Green=1, Blue=0, Purple=0\n- **Respondent 2**: Red=0, Yellow=1, Green=0, Blue=1, Purple=0\n- **Respondent 3**: Red=1, Yellow=1, Green=0, Blue=0, Purple=1\n\n**After merge in AddMaple (one multi-select column):**\n\n- **Respondent 1**: Red, Green\n- **Respondent 2**: Yellow, Blue\n- **Respondent 3**: Red, Yellow, Purple\n\nNotes:\n- Common encodings (`1/0`, `Y/N`, `TRUE/FALSE`) are recognized case-insensitively.\n- If some options are empty in your file (no respondents chose them), they won't affect the merge; you can still keep or hide those options in labels.\n\n---\n\n## Grouping related columns (grids / Likert scales)\n\nGrid questions are usually exported as one column per item with the **same response scale**. AddMaple keeps the columns separate but **groups** them so you can view and compare them together.\n\n### Example: product attribute ratings (Likert 1–5)\n\n**Raw export:**\n\n- **Respondent 1**: Ease of use=5, Value for money=4, Customer support=3\n- **Respondent 2**: Ease of use=4, Value for money=5, Customer support=4\n- **Respondent 3**: Ease of use=3, Value for money=3, Customer support=2\n\n**After grouping in AddMaple:**\n\n- Group title: **\"Please rate the following aspects of the product\"**\n- Group members (individual columns): *Ease of use*, *Value for money*, *Customer support* \n\nIn dashboards, the three items appear together. You can:\n- view them side-by-side,\n- filter by any item's value,\n- open any **single** item to analyze relationships on its own.\n\n---\n\n## Merge vs. Group: what's the difference?\n\n**Merge**\n- **What it does**: Combines many source columns that represent **one question** into **one column** (categorical or multi-select)\n- **Where you see the effect**: You work with a single variable everywhere (pivots, filters, charts)\n\n**Group**\n- **What it does**: Leaves columns **separate** but links them as a logical set (common stem/scale)\n- **Where you see the effect**: In dashboards, grouped items appear together; you can still analyze each column individually\n\n**Rule of thumb:** \nIf you see ten checkbox columns for one question, that's a **merge** case. \nIf you see several attributes rated on the same scale, that's a **group** case.\n\n---\n\n## Managing columns (review, fix, customize)\n\nOpen **Manage columns** from the dataset toolbar to inspect and adjust what AddMaple did.\n\n**You'll see**\n- The **original columns** from your file.\n- Any **merged columns** AddMaple created, with their member columns listed.\n- Any **groups**, with their member columns.\n- Detected **types** (numeric, categorical, text, date, boolean).\n\n**You can**\n- **Unmerge / re-merge**: split a merged column back to sources, or select sources and merge them.\n- **Group / ungroup**: add or remove columns from a logical group.\n- **Rename**:\n - *Group title* (e.g., shorten a long stem).\n - *Merged column name* (e.g., remove redundant prefixes).\n - *Category labels* (e.g., change `1`→`Strongly disagree`).\n- **Change type**:\n - Convert to **Date/Datetime** if a date was detected as text.\n - Convert **numeric codes** to categorical labels (or the reverse).\n - Set **Boolean** when headers contain Yes/No flags.\n- **Reorder categories** (e.g., Likert from *Strongly disagree* → *Strongly agree*).\n\nChanges apply immediately to charts, filters, and pivots.\n\n---\n\n## How titles are generated\n\nSurvey exports often repeat the **question stem** and the **answer label** in headers (e.g., `Q12_Product: Ease of use`, `Q12_Product: Value for money`). AddMaple:\n- extracts the common stem for the **group title**,\n- uses the varying part for **item names**,\n- and, for merges, derives a concise **merged column name**.\n\nYou can override any of these in **Manage columns**.\n\n---\n\n## Changing a column type (examples)\n\n- **Fix a date column** \n Detected as text? Change type to **Date**. If formats are mixed (e.g., `MM/DD/YYYY` and `DD/MM/YYYY`), standardize them in the source or split the column before upload.\n- **Code numeric Likert to labels** \n Values `1–5`? Change type to **Categorical** and set labels: `1=Strongly disagree … 5=Strongly agree`.\n- **Treat 1/0 flags as Boolean** \n Change type to **Boolean** to simplify filters and summaries.\n\n---\n\n## Common questions\n\n**The tool merged columns I don't want merged.** \nOpen **Manage columns** → select the merged column → **Unmerge**. Then merge only the columns that belong together.\n\n**A multi-select wasn't merged.** \nSelect the related checkbox columns in **Manage columns** → **Merge**. Ensure the headers correspond to the same question.\n\n**The group title is too long.** \nRename the group in **Manage columns**. Item names remain unchanged.\n\n**My dates look wrong.** \nChange the column type to **Date**. If the source mixes formats, standardize in the source file to avoid ambiguity.\n\n---\n"},"preparation/manage-columns":{"title":"Manage Columns","category":"Preparation","slug":"preparation/manage-columns","blurb":"Learn how to manage and configure your data columns in AddMaple.","order":2,"filename":"manage-columns.md","uid":"preparation/manage-columns","content":"\n# How to use Manage Column(s)\n\nAddMaple automatically detects and interprets your survey data when you first upload it. Most of the time this works well and you can start exploring right away. But sometimes survey exports are messy, and you may want to clean them up. For example, multi-select questions — those “choose all that apply” types — may be split into separate columns on export, and you may want to combine these into a single variable. Or grid questions may be displayed individually when you’d prefer to group them together to compare responses.\n\n**Manage Column(s)** is where you adjust columns in your dataset. This doesn’t change the underlying data — it only affects how the data is presented in your project. Think of it as the place to fix messy exports and make your dataset easier to work with. Your raw data remains unaltered, you can always revert back to the original state of the data. We show you the original column and category labels, so you can see which changes were made, and revert to the original formatting, if you need to. \n\n### Use this feature to:\n\n- **Rename columns** — shorten long question titles or replace cryptic labels like “Q12A_1” with something human-readable. \n- **Rename categories and values** — if exported data contain numeric codes instead of useful labels, such as (e.g. 1, 2, 3), you can edit these with better labels (e.g. “Yes”, “No”, “Maybe”).\n- **Hide/unhide items from the dashboard** — remove clutter from the Explore Dashboard and from drop-down menus (like filter selections). \n- **Combine columns from multi-select questions** — combine columns that belong to the same “choose all that apply” question. \n- **Group columns like Opinion Questions, together to visualize as one chart** — see how answers to related questions align on one Likert Scale chart, grouped box plots, dot plots, and fine-tune how individual labels appear within the group. \n- **Group similar column types from across your dataset** — for example, group questions where you used the same values across multiple columns, e.g. 1–5 rating questions, yes/no, numerical questions, such as 'What is your salary' to compare responses as a group.\n- **Adjust how numeric and date values are displayed** — create custom bins (e.g. age ranges, time periods) that make analysis easier. \n- **Use AI to clean and reorder categories** — let AI reorder implied scales (e.g. most agreement to least agreement) or classify inconsistent responses (like region or country names).\n- **Merge categories or values** - merge similar categories, or merge long-tail categories into an 'Other' category \n- **Reorder and lock category order** — override AddMaple’s default (most-to-least frequency) and keep categories in your preferred order. \n- **Change category colors for a specific column** — useful for coloring certain segments consistently (e.g. Segment A = yellow, Segment B = green). To apply brand colors project-wide so all charts and exports respect chosen colors, use **Manage Project**. \n\nYou can open **Manage Column(s)** in four ways: \n- From the dashboard: **More → Project Settings** \n- From the dashboard: hover over a column tile and click the **cog icon** in the bottom-left corner to be taken to that column's settings \n- From a pivot table or chart: click the **cog icon** in the legend tab on the right of the chart \n- From a pivot table or chart: **More → Column Settings** \n\n \n\nOnce open, you can: \n- Change the **name** or **type** of a column \n- [Hide or unhide columns](#hide-or-unhide-columns) \n- Adjust the [legend](../legend/legend) \n- [Combine columns](combining-columns) or split them \n- [Group columns](group) or ungroup them \n- For numeric or date columns: set [custom binning options](../data-types/custom-bins) \n- For groups: set the [group title](group) and the titles displayed for each column inside the group \n\n \n\nWhen you're done, click **Save** in the bottom-right. All changes apply across your project immediately. You can undo or adjust them anytime. \n\n---\n\n### Examples \n\n**1. Combine multiple columns into one variable** \nSuppose you've imported survey data where a multi-select question has been split into separate columns. In **Manage Column(s)**, you can combine these into one multi-select variable. Charts and tables across the project will then treat it as a single question, and PowerPoint exports will reflect the combined structure. \n\n \n\n**2. Apply custom binning** \nFor a numeric column like \"Age,\" you might want to view responses in ranges (e.g. 18–24, 25–34, 35–44) instead of every unique number. In **Manage Column(s)**, you can set custom bins to group numeric values or dates into ranges. \n\n \n\n\n**3. Hide metadata columns** \nSurvey exports often include metadata columns (e.g. response ID, timestamps). These aren't useful for analysis but clutter your dashboard. In **Manage Column(s)**, you can hide these columns. They remain in the dataset but won't appear in charts or pivots. \n\n \n\n**4. Change type and title** \nSometimes survey exports label variables unclearly (e.g. \"Q5_1\" instead of \"Satisfaction with product\"). In **Manage Column(s)**, you can rename the variable and change its type (for example, from text to categorical) so that it displays correctly in charts. \n\n \n\n---\n\n### Key points \n- Changes affect every chart, pivot table, and export in your project. \n- The raw data is never modified. \n- You can always undo or adjust settings. \n\n---\n"},"preparation/number-binning":{"title":"Number Binning","category":"Preparation","slug":"preparation/number-binning","blurb":"Learn how to configure how numeric columns are grouped into bins for analysis and visualization.","order":5,"filename":"number-binning.md","uid":"preparation/number-binning","content":"# Number Binning\n\nNumber binning allows you to group numeric values into ranges for easier analysis and visualization. Instead of analyzing every individual number, you can group them into meaningful ranges like age groups, income brackets, or satisfaction levels.\n\n---\n\n## Accessing Number Binning Settings\n\nYou can configure number binning in two ways:\n\n### Method 1: Column Settings (Recommended)\n1. **Click on the column header** of a numeric column\n2. **Select \"Column Settings\"** from the dropdown menu\n3. **Scroll to the \"Binning\" section**\n\n### Method 2: Manage Columns\n1. **More → Project Settings** from the dashboard\n2. **Select your numeric column**\n3. **Scroll to the \"Binning\" section**\n\n---\n\n## Binning Options\n\n### Auto (Recommended)\nUses the Freedman-Diaconis rule to create optimal bins based on your data distribution. You can optionally suggest a number of bins, and the system will approximate to it.\n\n**Features:**\n- **Optimal bin width**: Calculated using statistical best practices\n- **Adjustable bin count**: Use the slider to suggest more or fewer bins\n- **Outlier handling**: Option to collapse extreme outliers into separate bins\n\n**Best for:** Most use cases where you want statistically optimal grouping\n**Example:** Age data might be binned into 18-25, 26-35, 36-45, etc.\n\n### Equal Frequency\nCreates bins where each bin contains approximately the same number of data points.\n\n**Features:**\n- **Balanced distribution**: Each bin has similar counts\n- **Adjustable bin count**: Choose how many bins to create\n- **Good for skewed data**: Works well with uneven distributions\n\n**Best for:** When you want equal representation from each range\n**Example:** Income data where you want equal numbers in each income bracket\n\n### Fixed Width\nCreates bins of consistent width that you define.\n\n**Features:**\n- **Consistent intervals**: All bins have the same width\n- **Adjustable width**: Set the exact width for each bin\n- **Predictable ranges**: Easy to understand and interpret\n\n**Best for:** When you need consistent intervals for comparison\n**Example:** Test scores binned into 10-point ranges (0-10, 11-20, 21-30, etc.)\n\n### Custom\nDefine your own bin boundaries manually with full control over ranges and labels.\n\n**Features:**\n- **Custom ranges**: Set exact start and end values for each bin\n- **Custom labels**: Give meaningful names to each bin\n- **Flexible boundaries**: Create bins of different sizes\n- **Gap detection**: System warns about gaps between bins\n\n**Best for:** When you need specific business-defined ranges\n**Example:** Age groups: 18-24 (Young Adults), 25-34 (Early Career), 35-44 (Mid Career), etc.\n\n---\n\n## Live Preview\n\nThe binning interface shows a **live histogram preview** so you can see exactly how your data will be grouped before applying changes. This helps you:\n\n- Verify the number of bins created\n- Check that ranges make sense for your data\n- See the distribution of values across bins\n- Adjust settings until you're satisfied\n\n---\n\n## Examples\n\n### Example 1: Age Groups\n**Scenario:** You have age data and want to create age groups for analysis\n**Solution:** Use Custom bins with ranges like 18-24, 25-34, 35-44, 45-54, 55-64, 65+\n**Result:** Meaningful age groups instead of individual ages\n\n### Example 2: Income Brackets\n**Scenario:** You have income data and want equal representation in each bracket\n**Solution:** Use Equal Frequency with 5 bins\n**Result:** Five income brackets with similar numbers of people in each\n\n### Example 3: Test Scores\n**Scenario:** You have test scores and want consistent 10-point ranges\n**Solution:** Use Fixed Width with 10-unit width\n**Result:** Bins like 0-10, 11-20, 21-30, 31-40, etc.\n\n### Example 4: Likert Scale Analysis\n**Scenario:** You have 1-5 Likert scale data and want to group responses\n**Solution:** Use Custom bins: 1-2 (Low), 3 (Medium), 4-5 (High)\n**Result:** Simplified three-category analysis\n\n---\n\n## Tips for Number Binning\n\n### Choose the Right Method\n- **Auto**: For most cases where you want optimal statistical grouping\n- **Equal Frequency**: When you need balanced representation across ranges\n- **Fixed Width**: When you need consistent intervals for comparison\n- **Custom**: When you have specific business requirements or meaningful ranges\n\n### Consider Your Data Distribution\n- **Normal distribution**: Auto mode works well\n- **Skewed data**: Equal Frequency or Custom might be better\n- **Sparse data**: Custom bins can help group sparse values\n- **Dense data**: Auto or Fixed Width work well\n\n### Think About Your Audience\n- **Business users**: Custom bins with meaningful labels\n- **Statistical analysis**: Auto mode for optimal grouping\n- **Comparisons**: Fixed Width for consistent intervals\n- **Reporting**: Equal Frequency for balanced representation\n\n---\n\n## Advanced Features\n\n### Outlier Handling (Auto Mode)\nWhen using Auto mode, you can enable \"Collapse extreme outliers\" to:\n- Identify extreme values using statistical methods\n- Group outliers into separate bins\n- Adjust sensitivity with the outlier threshold (k-value)\n- Prevent outliers from distorting your main analysis\n\n### Custom Bin Management\nWhen using Custom mode, you can:\n- **Add bins**: Click \"Add Bin\" to create new ranges\n- **Remove bins**: Click the minus icon to delete bins\n- **Fix gaps**: Automatically adjust bin boundaries to eliminate gaps\n- **Sort bins**: Arrange bins by their range values\n- **Create equal bins**: Automatically generate equal-width bins across your data range\n\n---\n\n## Common Use Cases\n\n### Demographic Analysis\n- **Age groups**: 18-24, 25-34, 35-44, 45-54, 55-64, 65+\n- **Income brackets**: Custom ranges based on your market\n- **Education levels**: Grouped by years or categories\n\n### Survey Analysis\n- **Likert scales**: Group 1-5 scales into Low/Medium/High\n- **NPS scores**: Group 0-10 into Detractors/Passives/Promoters\n- **Satisfaction ratings**: Custom ranges based on your benchmarks\n\n### Performance Metrics\n- **Test scores**: Consistent point ranges (0-20, 21-40, 41-60, etc.)\n- **Sales performance**: Custom ranges based on your targets\n- **Customer ratings**: Grouped into meaningful categories\n\n---\n\n## Troubleshooting\n\n**My bins are too granular/fine**\n- Try Auto mode with fewer bins\n- Use Fixed Width with larger width\n- Combine adjacent bins in Custom mode\n\n**My bins are too broad**\n- Try Auto mode with more bins\n- Use Fixed Width with smaller width\n- Split bins in Custom mode\n\n**Some bins are empty**\n- This is normal for sparse data\n- Consider using Equal Frequency for better distribution\n- Check if your data range is appropriate for the binning method\n\n**My data looks wrong**\n- Ensure your column is detected as Numeric type\n- Check for non-numeric values in your data\n- Use Manage Columns to change the column type if needed\n\n**Outliers are distorting my bins**\n- Enable \"Collapse extreme outliers\" in Auto mode\n- Adjust the outlier threshold sensitivity\n- Use Custom mode to manually handle outliers\n"},"preparation/schema-files":{"title":"Schema Files","category":"Preparation","slug":"preparation/schema-files","blurb":"Upload a schema file to map survey questions to your data columns and automatically apply meaningful labels and grouping.","order":9,"filename":"schema-files.md","uid":"preparation/schema-files","content":"\n# Using schema files to enhance your data\n\nIf you have a separate schema file (often called a \"question key\" or \"data dictionary\") that describes your survey questions, you can upload it to AddMaple to automatically apply descriptive labels, group related questions, and organize your columns.\n\n**This is useful when** your CSV export uses technical column names (like `q7_industry` or `TechEndorse_1`) but you have a separate file that contains the full question text and metadata.\n\n---\n\n## What is a schema file?\n\nA schema file is a CSV that maps your data's column names to human-readable information. Common sources include:\n\n- **Question keys** from survey platforms (User Interviews, Qualtrics, SurveyMonkey)\n- **Data dictionaries** from research teams\n- **Codebooks** from SPSS or statistical packages\n- **Schema exports** from survey builders\n\n### Example schema file\n\n```csv\nQuestion,Question Text,Type\nscreener_1,Which statement reflects your relationship to research?,Multiple Choice\nscreener_2,What type of research do you primarily conduct?,Multi-select\nq1_title,Which is closest to your job title?,Multiple Choice\nq7_industry,Which industry category describes your company?,Dropdown\n```\n\n---\n\n## Uploading a schema file\n\n1. **Open Project Settings** (More → Settings)\n2. **Navigate to the \"Manage Project\" tab**\n3. **Scroll to \"Upload Schema File\"**\n4. **Click \"Upload Schema\"**\n\nA schema mapper will appear where you can:\n- **Upload your schema CSV file**\n- **Map schema columns to AddMaple fields**\n- **Preview the mapping** before applying\n\n---\n\n## Mapping schema columns\n\nThe schema mapper shows your CSV columns and lets you assign each one to a specific field:\n\n### Required field\n- **Column Name (rawName)** — Must match your data's column headers exactly\n\n### Recommended fields\n- **Display Label** — Human-readable name shown in AddMaple\n- **Question Text** — Full question wording (used for grouping)\n\n### Optional fields\n- **Group ID** — Groups related sub-questions together (matrix questions)\n- **Group Label** — Display name for the group\n- **Short Label** — Abbreviated version of the label\n- **Semantic Category** — Classification or theme\n- **Tags** — Comma or semicolon-separated keywords\n- **Order** — Numeric order for sorting within groups\n- **Hidden** — Set to \"true\" to hide the column by default\n\n---\n\n## How schema mapping works\n\nAfter you upload and map a schema file, AddMaple will:\n\n1. **Match columns** — Find each data column using the rawName from your schema\n2. **Apply labels** — Replace technical names with descriptive question text\n3. **Create groups** — Organize related questions using Group ID and order\n4. **Update settings** — Regenerate column configuration with schema metadata\n\nThe page will reload automatically with your updated column settings.\n\n---\n\n## Example use cases\n\n### Use case 1: Survey with question codes\n\n**Your data export:**\n- Column names: `screener_1`, `screener_2_market_r`, `q1_title`, `q7_industry`\n\n**Your schema file:**\n```csv\nColumn,Question\nscreener_1,Which statement reflects your relationship to research?\nscreener_2,What type of research do you primarily conduct?\nq1_title,Which is closest to your job title?\nq7_industry,Which industry describes your company?\n```\n\n**Mapping:**\n- Column Name → \"Column\"\n- Display Label → \"Question\"\n\n**Result:**\nColumns display with full question text instead of technical codes.\n\n---\n\n### Use case 2: Grouped matrix question\n\n**Your data export:**\n- Columns: `TechEndorse_1`, `TechEndorse_2`, `TechEndorse_3`, `TechEndorse_4`\n\n**Your schema file:**\n```csv\nqname,question,sub,group_id,order\nTechEndorse_1,What attracts you to a technology?,AI integration,QID18,1\nTechEndorse_2,What attracts you to a technology?,Easy-to-use API,QID18,2\nTechEndorse_3,What attracts you to a technology?,Robust API,QID18,3\nTechEndorse_4,What attracts you to a technology?,Quality reputation,QID18,4\n```\n\n**Mapping:**\n- Column Name → \"qname\"\n- Display Label → \"sub\"\n- Question Text → \"question\"\n- Group ID → \"group_id\"\n- Group Label → \"question\"\n- Order → \"order\"\n\n**Result:**\nFour sub-questions grouped together under \"What attracts you to a technology?\" with proper ordering.\n\n---\n\n### Use case 3: Multi-select with option labels\n\n**Your data export (double-header format):**\n- Row 1: `screener_2_market_r`, `screener_2_user_ux`, `screener_2_data_science`\n- Row 2: `Market research`, `User/UX research`, `Data science`\n\n**Your schema file:**\n```csv\nQuestion,Question Text\nscreener_2,What type of research do you primarily conduct?\n```\n\n**Steps:**\n1. First, set **Header rows to 2** in Project Settings\n2. Then upload schema file\n3. Map: Column Name → \"Question\", Display Label → \"Question Text\"\n\n**Result:**\nIndividual checkbox columns merge into a single multi-select column with:\n- Column name: \"What type of research do you primarily conduct?\"\n- Values: \"Market research\", \"User/UX research\", \"Data science\" (from Row 2)\n\n---\n\n## Schema file formats\n\nAddMaple supports flexible schema formats. Here are common patterns:\n\n### Minimal schema (column names and labels)\n```csv\ncolumn,label\nq1,Job title\nq2,Years of experience\nq3,Industry\n```\n\n### Full schema (with grouping)\n```csv\ncolumn_name,display_label,question_text,group_id,group_label,order\nTechEndorse_1,AI integration,What attracts you?,QID18,What attracts you?,1\nTechEndorse_2,Easy API,What attracts you?,QID18,What attracts you?,2\n```\n\n### Question key (simple format)\n```csv\nQuestion,Question Text\nscreener_1,Which statement reflects your relationship to research?\nq7_industry,Which industry describes your company?\n```\n\n**For multi-select questions**, the schema typically lists the base question (like `screener_2`) and AddMaple automatically matches related columns (like `screener_2_market_r`, `screener_2_user_ux`) through prefix matching.\n\n---\n\n## Tips for preparing schema files\n\n- **Exact column name match** — The rawName field must match your data's column headers exactly (including underscores, capitalization)\n- **One row per column** — For multi-select questions, you can list either the base question or each individual option column\n- **CSV format** — Save as CSV (not Excel) for reliable upload\n- **Remove blank rows** — Empty rows in the schema will be skipped\n- **Prefix matching** — For multi-select splits like `q3_career_change_promotion`, list the base `q3_career_change` and AddMaple will match all related columns\n\n---\n\n## Common schema mappings\n\nDifferent survey platforms export different schema formats. Here's how to map them:\n\n### Simple question key format\n```csv\nQuestion,Question Text,Notes,Type\nscreener_1,Which statement reflects your relationship to research?,Select one,Multiple Choice\n```\n**Mapping:** Column Name → \"Question\", Display Label → \"Question Text\"\n\n### Matrix question format (with grouping)\n```csv\nqid,qname,question,sub,sq_id\nQID18,TechEndorse_1,What attracts you to a technology?,AI integration,1\n```\n**Mapping:** Column Name → \"qname\", Display Label → \"sub\", Question Text → \"question\", Group ID → \"qid\", Order → \"sq_id\"\n\n### Research codebook format\n```csv\nvariable,label,category,hide\nparticipant_id,Participant ID,identifier,true\nage,Age in years,demographic,false\n```\n**Mapping:** Column Name → \"variable\", Display Label → \"label\", Semantic Category → \"category\", Hidden → \"hide\"\n\n---\n\n## After applying a schema\n\nOnce you apply a schema file:\n\n- **Columns update immediately** with new labels and grouping\n- **The page reloads** to reflect changes\n- **Multi-select questions** use descriptive option labels instead of column IDs\n- **Matrix questions** appear as grouped sub-questions\n- **You can still edit** individual columns manually in Manage Columns if needed\n\n**Important:** Applying a schema regenerates all column settings. Any manual edits you've made to column names, types, or grouping will be replaced with the schema's definitions.\n\n---\n\n## Troubleshooting\n\n**My columns didn't update**\n- Verify the rawName in your schema matches the actual column headers in your data exactly\n- Check for extra spaces or different capitalization\n- For multi-select splits, try listing the base column name without suffixes\n\n**Some columns are missing**\n- Ensure every column in your data has a corresponding row in the schema\n- Columns without schema entries will keep their original auto-detected names\n\n**Groups aren't appearing**\n- Make sure you mapped both Group ID and Group Label fields\n- Verify all columns in a group share the same Group ID value\n- Add Order values if you want to control the sequence within groups\n\n**Multi-select values show column IDs instead of labels**\n- If using double headers, set Header rows to 2 first, then apply the schema\n- The second header row provides the descriptive option labels\n\n---\n\n## Related features\n\n- [**Header Rows**](header-rows) — Configure multi-row headers before uploading schema\n- [**Manage Columns**](manage-columns) — Manually edit column settings after schema application\n- [**Combining Columns**](combining-columns) — Understand how multi-select merging works\n- [**Group**](group) — Learn about grouped matrix questions\n\n"},"preparation/weighting":{"title":"Weighting","category":"Preparation","slug":"preparation/weighting","blurb":"Apply respondent weights to your survey data for more accurate analysis and statistical testing.","order":7,"filename":"weighting.md","uid":"preparation/weighting","content":"\n# How to use Weighting\n\nWeighting allows you to adjust your survey results to better represent your target population. This is especially useful when certain groups are over- or under-represented in your sample, or when you need to match demographic distributions from census data.\n\nYou can set your weight column in the **Manage Project** tab — the same place where you configure [color presets](./colors). Go to **More menu → Project Settings → Manage Project**.\n\n\n\n## How weighting works\n\nWhen you select a numeric column as your weight column, AddMaple applies those weights to all your analyses:\n\n- **Charts and pivot tables** — All counts and percentages are calculated using weighted values\n- **Statistical tests** — t-tests, chi-square tests, correlations, and ANOVA use weighted calculations\n- **Cross-tabulations** — Every cell in your tables reflects the weighted sample\n- **Exports** — PowerPoint presentations and data exports include weighted results\n\nThe weight column must contain numeric values greater than zero. Rows with missing, zero, or negative weights are treated as having a weight of 1.\n\n**Note:** Currently, AddMaple doesn't calculate weights for you — you need to create your own weight column. However, automatic weight calculation will be available soon, making it easier to generate weights based on demographic targets.\n\n## Setting up weights\n\n1. **Choose your weight column** — Select a numeric column from the dropdown (only numeric columns are available)\n2. **Save your changes** — Click **Save** in the bottom right to apply weights across your project\n\n\n\n\n## Examples\n\n**1. Demographic weighting**\nSuppose you surveyed 1,000 people but your sample has too many young respondents and not enough older ones. You can create a weight column where:\n- 18-34 year olds get a weight of 0.8 (reducing their influence)\n- 35-54 year olds get a weight of 1.0 (normal representation) \n- 55+ year olds get a weight of 1.3 (increasing their influence)\n\n**2. Response rate adjustment**\nIf certain groups had lower response rates, you might weight them higher to compensate. For example:\n- Online responses: weight of 1.0\n- Phone responses: weight of 1.2 (they're harder to reach)\n- In-person responses: weight of 1.1 (moderate difficulty)\n\n**3. Geographic weighting**\nTo match national demographics, you might weight respondents based on their region:\n- Urban areas: weight of 0.9\n- Suburban areas: weight of 1.1 \n- Rural areas: weight of 1.2\n\n## Statistical considerations\n\nAddMaple uses sophisticated weighted statistical methods:\n\n- **Weighted t-tests** — Uses Kish effective sample size and Welch-Satterthwaite degrees of freedom\n- **Weighted correlations** — Calculates Pearson correlations using weighted means and variances\n- **Weighted chi-square tests** — Applies weights to contingency table calculations\n- **Weighted ANOVA** — Uses weighted group means and variances\n\nThese methods ensure your statistical tests account for the weighting scheme and provide accurate p-values.\n\n## Best practices\n\n- **Check your weights** — Extreme weights (>5.0 or <0.2) can distort results\n- **Document your approach** — Note why you're weighting and how weights were calculated\n- **Test sensitivity** — Try different weighting schemes to see how results change\n- **Consider effective sample size** — Heavy weighting reduces your effective sample size\n\n## Removing weights\n\nTo stop using weights, simply select **\"None\"** from the weight column dropdown and save. All analyses will return to unweighted calculations.\n\n---\n\n### Key points\n- Weights apply to all charts, tables, and statistical tests in your project\n- Only numeric columns can be used as weight columns \n- Weights must be positive numbers (missing or invalid values default to 1)\n- Statistical tests use weighted methods to ensure accuracy\n\n---\n"},"report/citation":{"title":"How to Cite AddMaple in Your Work","category":"Report","slug":"report/citation","blurb":null,"order":4,"filename":"citation.md","uid":"report/citation","content":"# Report\n\n### How to Cite AddMaple in Your Work\n\nThank you for using AddMaple in your research! Below are the recommended citation formats:\n\n**APA Style**\n\nAddMaple Core Team. (Year). *AddMaple: Advanced data analysis software*. Retrieved from https://addmaple.com\n\n**MLA Style**\n\n*AddMaple: Advanced Data Analysis Software*. AddMaple Core Team, [year], https://addmaple.com.\n\n**Chicago Style**\n\nAddMaple Core Team. *AddMaple: Advanced Data Analysis Software*. Accessed [date]. https://addmaple.com.\n\n**BibTeX (for LaTeX users)**\n\n```\n@misc{addmaple,\n author = {AddMaple Core Team},\n title = {AddMaple: Advanced Data Analysis Software},\n year = {Year},\n url = {https://addmaple.com}\n}\n```\n\n**Download Citation Files**\n\nTo make citing AddMaple even easier, you can download ready-to-use citation files for your reference manager:\n\n• [RIS Format (.ris)](https://addmaple.com/citation/AddMaple.ris)\n\n• [EndNote Format (.enw)](https://addmaple.com/citation/AddMaple.enw)\n\n \n\nThese files are compatible with popular tools like EndNote, Zotero, and Mendeley.\n\n \n\n**Why Cite AddMaple?**\n\nCiting the tools you use promotes transparency and ensures others can replicate your results. \n\n \n\nIf you have questions, contact us at [hello@addmaple.com](mailto:hello@addmaple.com)\n"},"report/reportaddchart":{"title":"Adding a chart to your report","category":"Report","slug":"report/reportaddchart","blurb":null,"order":1,"filename":"reportaddchart.md","uid":"report/reportaddchart","content":"# Adding a chart to your report\n\nTo add a chart to your report, simply navigate to the chart you want to add, click the More menu and click \"Add To Report\".\n\n\n\n\n### Filters\n\nNote that your chart will include any filters that you have active when you click \"Add to report\"."},"report/reportexplorable":{"title":"How to make your data explorable","category":"Report","slug":"report/reportexplorable","blurb":null,"order":2,"filename":"reportexplorable.md","uid":"report/reportexplorable","content":"# How to make your data explorable\n\nYou can let viewers of your report also explore your data using AddMaples tools. \n\nWe support selecting 12 columns to make explorable. Please remember that any data that you make explorable will be visible at the row level - therefore if a report is going to be shared with a wider audience we advise against selecting columns with personally identifiable information.\n\nClick on \"Report Settings\" and you will see the options for \"Explorable Data\"\n\n\nYou can then select up to 12 columns to be made \"explorable\" by your report viewers\n\n\nAfter clicking \"Make Data Explorable\" your selected columns will be securely uploaded to AddMaple's systems and when viewing your report there will be a link in the top right that says \"Analyze this dataset\". Clicking that link will show your selected columns in the full AddMaple interface.\n"},"report/reportpublish":{"title":"Publishing a report","category":"Report","slug":"report/reportpublish","blurb":null,"order":3,"filename":"reportpublish.md","uid":"report/reportpublish","content":"# Publishing a report\n\nReports are unpublished by default. To publish, simply click the \"Publish\" button - the url of your published report will then be made visible.\n\n\n\n\nTo set a password for your report, click on \"report settings\" and set your desired password:\n\n\n"},"row-by-row/addfilterrow":{"title":"Adding a filter from the row view","category":"Row by Row","slug":"row-by-row/addfilterrow","blurb":"From row view, click a value or use the stacked chart to add filters and refine your selection.","order":2,"filename":"addfilterrow.md","uid":"row-by-row/addfilterrow","content":"# Adding a filter from the row view\n\nYou can add a filter by clicking on the value for a particular column\n\n\n\nYou can also use the stacked bar chart on the right to filter by other values for the same column\n\n"},"row-by-row/navigaterows":{"title":"Navigating between rows","category":"Row by Row","slug":"row-by-row/navigaterows","blurb":"Move between records with Next/Previous—especially useful after applying filters to narrow your dataset.","order":3,"filename":"navigaterows.md","uid":"row-by-row/navigaterows","content":"# Row by Row\n\n### Navigating between rows\n\nIn row by row view you can navigate between rows through the **Next **and **Previous **buttons. \n\nThis is particularly useful when you've filtered down to a smaller segment of your dataset.\n\n\n"},"row-by-row/understandrow":{"title":"Understanding the row by row view","category":"Row by Row","slug":"row-by-row/understandrow","blurb":null,"order":1,"filename":"understandrow.md","uid":"row-by-row/understandrow","content":"# Understanding the row by row view\n\nThis view allows you to see a single \"row\" from you data in a vertical view. This is a lot easier than a traditional spreadsheet (table) view and allows you to dive into a specific row to see the results for all columns for that row.\n\nIn addition we give you the context on the right of how the value for a column for this row relates to the overall dataset. \n\nFor example in this dataset we can see that this row has a \"Device Type\" of \"Tablet\". However we can see that only 10% of the dataset also has the value of \"Tablet\".\n\n\n"},"sentence-builder/addfilterdashboard":{"title":"Adding a Filter","category":"Sentence Builder","slug":"sentence-builder/addfilterdashboard","blurb":"Add a filter from the top menu or by clicking a bar on an expanded chart.","order":3,"filename":"addfilterdashboard.md","uid":"sentence-builder/addfilterdashboard","content":"# Adding a Filter\n\nTo add a filter you can click the **Filter** button at the top of the screen (or press the / key to open the filter menu)\n\n\nAlternatively, if you expand a column, you can click on one of the bars to instantly filter.\n"},"sentence-builder/addpivot":{"title":"Adding a pivot","category":"Sentence Builder","slug":"sentence-builder/addpivot","blurb":"Add a new pivot from the top menu, pick a column, and see the chart update instantly.","order":2,"filename":"addpivot.md","uid":"sentence-builder/addpivot","content":"# Adding a pivot\n\nYou can add a pivot no matter what screen you are on in AddMaple by clicking the **Pivot** button at the top of the screen. Learn more about [pivoting your data](../frequently-asked-questions/how-to-pivot-your-data) and [filtering your data](../frequently-asked-questions/filter-your-data).\n\nClick the **Pivot** button at the top of the screen\n\n\nThis will add a new pivot dropdown menu to the sentence bar, click \"Please select\" and you will be shown all the columns in your dataset.\n\n\nYou can either type to search for your column or scroll down to find it.\n\n\nEither press enter or click the column you'd like to pivot by and you will be taken to a pivot chart.\n"},"sentence-builder/aggregation":{"title":"How to aggregate by another column","category":"Sentence Builder","slug":"sentence-builder/aggregation","blurb":"Choose an aggregation (Total, Average, Median, or Count Unique) and select a column to summarize your pivot.","order":1,"filename":"aggregation.md","uid":"sentence-builder/aggregation","content":"# Sentence Builder\n\n### How to aggregate by another column\n\nAddMaple allows you to aggregate one column by another. For example if you have a numeric column - Salary, and a categorical column - Age Range, you can use AddMaple to view median salary by age range.\n\nYou can aggregate from any pivot chart by clicking on the \"Number of\" button in the sentence bar.\n\n\nThis will bring up the aggregation options.\n\n1. Total amount of - this is like SUM on a spreadsheet, when you select this you will be given a list of numeric columns to choose from\n\n1. Average - this is like AVERAGE on a spreadsheet and calculates the mean. After selecting you will give given a list of numeric columns to choose from\n\n1. Median - this calculates the median and also requires you to select a numeric column\n\n1. Count of unique - this allows you to aggregate by a categorical column. There is an example further down in this guide.\n\n \n\n\nOnce you select an aggregation type, AddMaple will add another dropdown allowing you to select your aggregation column.\n\n\nIn this example we can see the median annual compensation per age range.\n\n\nThis is another example showing the \"Count Unique\" aggregation option. Here we can see the unique industries represented per database environment (this is from a developer survey).\n\n"},"sentence-builder/how-to-remove-long-tail":{"title":"How to remove the long tail","category":"Sentence Builder","slug":"sentence-builder/how-to-remove-long-tail","blurb":"Filter out small categories using \"has more than\" to keep charts readable and enable valid statistical tests.","order":4,"filename":"how-to-remove-long-tail.md","uid":"sentence-builder/how-to-remove-long-tail","content":"# How to remove the long tail\n\nIn survey data, you might have a column with many small categories that only have a few responses each. For example, a global survey with a country question could include many countries with very few respondents. Filtering out these smaller categories can be helpful because:\n\n• Small categories may prevent statistical tests, like Chi-Square, from working properly.\n\n• Charts and tables can become too large and difficult to read.\n\nYou can filter out categories with a small number of responses as follows:\n\nThis is an example of a country column with a long tail of responses. You can see from the stats box that there are 186 categories and that the median count per category is only 39.5, despite the average (mean) being 351. This shows that there is a long tail.\n\n\nThe first step is to add a filter, this can be done by clicking the **Filter** button at the top of the screen.\n\n\nSelect the column that you would like to filter (country in this case). Then select \"has more than\" for the filter type. Then add the minimum number of responses per category, in this example we chose 200.\n"},"sharing-and-exporting/download":{"title":"Download or Export Data","category":"Sharing and Exporting","slug":"sharing-and-exporting/download","blurb":null,"order":1,"filename":"download.md","uid":"sharing-and-exporting/download","content":"# Sharing and Exporting\n\n### Download or Export Data\n\nAddMaple allows you to export or download your data in a variety formats including CSV and XLSX (Excel).\n\nTo convert from a SAV to a CSV file, simply open your SAV file with AddMaple and follow the instructions in this guide.\n\nTo download your data, click the More menu and select \"Download Dataset\"\n\n\nIf you have a premium AddMaple subscription you will see the following popup box. You can choose to download all columns, or select specific columns to download. \n\nAddMaple also respects any filters you have applied. For example if you have filtered a dataset to only show results where Country = USA, then your downloaded data will only have those results. If you want to download the full dataset make sure you clear any filters.\n\n\nSelect the type of file you would like to download. AddMaple supports exporting to CSV, Excel, JSON, Parquet or own AddMaple file types.\n\nWe have two AddMaple file types:\n\n1. Fast - this file type makes loading large files super fast. If you have a large CSV or SAV file then converting it to AddMaple Fast will mean that your data loads much faster\n\n1. Compressed - this is the smallest file size, smaller than SAV or Parquet.\n\n \n\n"},"sharing-and-exporting/excel-crosstabs":{"title":"Export Crosstabs (Excel)","category":"Sharing and Exporting","slug":"sharing-and-exporting/excel-crosstabs","blurb":"Generate a formatted Excel workbook of crosstabs from your dataset, respecting filters and brand colors.","order":2,"filename":"excel-crosstabs.md","uid":"sharing-and-exporting/excel-crosstabs","content":"\n# Export Crosstabs (Excel)\n\nCreate a formatted Excel workbook of crosstabs so you can share results or continue analysis outside AddMaple. The export respects your current filters and uses your project brand color.\n\n## Open the tool\n\n1. Click the **More** menu.\n2. Choose **Export Crosstabs (Excel)**.\n\nThis opens a panel where you select question columns and banner columns, then download a ready-to-use XLSX file.\n\n## Step 1 — Select Questions\n\nChoose the columns to use as questions (rows). We recommend categorical questions:\n\n- Single choice categories\n- Opinion scales (Likert)\n\nAddMaple filters the list to exclude free-text, id/unique, and time-only columns.\n\n## Step 2 — Select Banners\n\nChoose the columns to use as banners (columns across the top). Banners can be:\n\n- Categorical and Multi‑tag\n- Numeric (auto‑binned)\n- Date (auto‑binned)\n\nTip: Pick banners you commonly use for cuts (e.g., segment, market, wave, device).\n\n## Download the workbook\n\nClick **Download Excel**. The export includes:\n\n- One or more worksheets with crosstabs for each selected question\n- Counts and percentages by banner category\n- Clean formatting and your project's primary brand color\n\nNotes:\n\n- Exports respect any filters currently applied. Clear filters to export the full dataset.\n- Selecting multiple questions creates multiple worksheets in the same workbook.\n\n## Tips\n\n- Start with 1–2 banners to keep tables readable, then expand.\n- If a banner is numeric or a date, AddMaple auto‑bins it into useful ranges.\n- Ensure question columns are categorical or scale‑based for clearer tables.\n\nAvailability: Export Crosstabs is limited to certain plans.\n\n\n"},"sharing-and-exporting/guess-chart":{"title":"Share Guess Charts","category":"Sharing and Exporting","slug":"sharing-and-exporting/guess-chart","blurb":"Create interactive quiz charts where viewers guess the answer before revealing your data visualization.","order":3,"filename":"guess-chart.md","uid":"sharing-and-exporting/guess-chart","content":"\n# Share Guess Charts\n\nCreate engaging, interactive charts that hide the results until viewers guess the answer. Perfect for presentations, training sessions, or making data exploration more fun.\n\n## What are Guess Charts?\n\nGuess Charts let you share a chart with a built-in quiz. Viewers see a question with multiple choice options and must make their guess before the chart is revealed. This creates an interactive experience that encourages engagement and helps viewers think about the data before seeing the results.\n\n## Creating a Guess Chart\n\nTo create a Guess Chart:\n\n1. **Navigate to your chart** — Open any chart you want to share\n2. **Click the Share button** — Look for the Share icon in the chart actions menu\n3. **Select \"Share Guess Chart\"** — Choose this option from the Share dropdown menu\n4. **Configure your quiz** — Set up the question, options, and correct answer\n\n\n\n## Setting Up Your Quiz\n\nWhen you select \"Share Guess Chart\", AddMaple opens the sharing dialog with guess mode enabled. You'll see several options to customize:\n\n### 1. Give Your Chart a Title\n\nEnter a descriptive title that will appear when the chart is shared. This helps viewers understand what they're looking at.\n\n### 2. Enable Guess Mode\n\nToggle the \"Enable guess mode\" switch to activate the quiz functionality. This option only appears when your chart has multiple categories or options to choose from.\n\n### 3. Write Your Question\n\nCreate a clear question that viewers will answer. For example:\n- \"Which category received the highest score?\"\n- \"What was the most popular response?\"\n- \"Which region had the largest increase?\"\n\nThe question should relate directly to what your chart shows.\n\n### 4. Choose the Correct Answer\n\nSelect the correct answer from the dropdown menu. AddMaple automatically populates this list with options from your chart data, making it easy to select the right answer.\n\n### 5. Customize Instructions\n\nWrite instructions that will appear below the question. The default message explains that viewers should guess the answer to reveal the chart. You can customize this to match your style or add specific context.\n\n## How Viewers Experience Guess Charts\n\nWhen someone opens your shared Guess Chart link:\n\n1. **They see the question** — The quiz question appears prominently at the top\n2. **They view the options** — Multiple choice options are displayed as clickable buttons\n3. **They make their guess** — Clicking an option reveals whether they were correct\n4. **The chart appears** — After the result is shown, the full chart is revealed automatically\n\nThe experience is smooth and engaging, with visual feedback showing correct and incorrect answers before transitioning to the chart view.\n\n## When to Use Guess Charts\n\nGuess Charts work great for:\n\n- **Presentations** — Engage your audience before revealing key insights\n- **Training sessions** — Help people think critically about data before seeing results\n- **Social sharing** — Create interactive content that encourages clicks and engagement\n- **Educational content** — Teach data literacy by having viewers predict outcomes\n\n## Technical Notes\n\n- Guess Charts work with any chart that has multiple categories or options\n- Options are automatically extracted from your chart data (up to 10 options)\n- The chart remains hidden until the viewer makes a guess\n- All shared charts respect your project's color settings and styling\n- Guess Charts can be embedded in web pages just like regular shared charts\n\n"},"stats/anovatest":{"title":"How to run an ANOVA test","category":"Stats","slug":"stats/anovatest","blurb":null,"order":5,"filename":"anovatest.md","uid":"stats/anovatest","content":"# How to run an ANOVA test\n\nAddMaple will automatically run an ANOVA test when you pivot by a categorical column and a numeric column.\n\nIn this example we are exploring a salary dataset and have pivoted by **Salary **and **Education Level**\n\n\n\nAddMaple will display the summary of the ANOVA test in the legend on the right:\n\n\n\nClick \"See more\" to go to the stats tab where you will see further details. AddMaple will give you an explanation of the test that has been performed and the results. In this example there is a strong relationship between Salary and Education Level.\n\n\n\nYou can view the numeric results below the text explanation. \n\nFor ANOVA we calculate:\n\n- P-Value: the measure of probability as to whether the relationship between two columns is due to chance or not.\n\n- F-Score: this compares the variation between group averages to the variation within the groups themselves. A higher F-Score means the differences are less likely to be due to chance.\n\n- Eta-Squared: this indicates the strength of the relationship between categorical groups and numerical data. It shows what proportion of the total variance in the numerical data can be explained by the differences between the categorical groups.\n\n\n\nWe also perform Tukeys HSD on the categories. This determines which pair of categories have the most significant differences. In this example we can see that the most significant difference in salaries was between those with a Bachelor's degree vs those with a Master's.\n\n\n\n \n\n \n\n "},"stats/chi-square":{"title":"Chi-Square Test","category":"Stats","slug":"stats/chi-square","blurb":null,"order":4,"filename":"chi-square.md","uid":"stats/chi-square","content":"# Chi-Square Test\n\nAddMaple runs chi-square tests for you automatically to determine whether there is a significant relationship between two categorical columns and the strength of that relationship.\n\nTo get started simply pivot two columns together:\n\n\n\nIf the columns are categorical, then AddMaple will run the chi-square test and give you an overview of the result in the legend\n\n\n\nClick \"see more\" to get more details behind the calculation.\n\nThis will take you to the stats tab which explains why we've run the test and the result.\n\n\n\nIf you scroll down you will see the numeric results:\n\n- P-Value - the measure of probability as to whether the relationship between two columns is due to chance or not\n\n- Cramér's V - the strength of the relationship between two categorical columns, giving a value from 0 (no relationship) to 1 (perfect relationship)\n\n- Chi Square Statistic - the difference between the actual counts and the counts you would expect if there were no relationship (null hypothesis) in the categorical data.\n\n- Degrees of Freedom - the number of values in a calculation that are free to vary. In the Chi-Square test, it is calculated based on the number of categories in each variable\n\n- Expected values under 5 - the percentage of expected values that are less than 5 (this should be less than 20% for the test to be accurate)\n\n- Expected values under 1 - the percentage of expected values that are less than 1 - this should be 0 for the test to be accurate (you may need to filter out categories with small numbers of results by clicking the **Filter** button at the top of the screen)\n\n\n\n## Further Insights Between Column Categories\n\nWhen you have more than two categories in your pivot, AddMaple provides additional analysis to identify which specific categories are driving the significant relationship. Click the toggle **\"Further Insights Between Column Categories\"** to see a detailed breakdown.\n\nThis analysis compares each category against all the other categories combined to determine which ones are significantly different from the rest. The results are ordered by the level of difference, showing you:\n\n- **Category**: The specific category being analyzed\n- **Level of difference**: Strong, Moderate, or None (based on statistical significance and effect size)\n- **P-value**: The statistical significance of that category's difference from the rest\n- **V-value**: The effect size (Cramér's V) showing the strength of the relationship for that specific category\n\nFor example, if you're analyzing \"Job Category\" vs \"Satisfaction Level\", this feature will show you that \"Manager\" has a strong relationship with satisfaction while \"Software Engineer\" shows no significant difference from the overall pattern.\n\nThis helps you understand not just that there's a relationship between your columns, but which specific categories are most responsible for driving that relationship."},"stats/clustering-methods-explained":{"title":"Understanding Clustering Methods","category":"Stats","slug":"stats/clustering-methods-explained","blurb":"Deep dive into how each clustering algorithm works, when to use it, and what it finds in your data.","order":8,"filename":"clustering-methods-explained.md","uid":"stats/clustering-methods-explained","content":"\n# Understanding Clustering Methods\n\nAddMaple offers four algorithms to discover natural groupings in your data. Here's how each one works, explained without the jargon.\n\n**Looking for a quick start?** See [Clustering](./clustering.md) for step-by-step instructions on using the clustering tool.\n\n## K-Means: The Centroid Champion\n\n**What it does:** K-Means divides your data into exactly `k` groups by finding the \"center point\" of each group and assigning rows to their nearest center.\n\n**How it works (step by step):**\n\n1. Pick `k` random starting points (centers) scattered throughout your data\n2. Assign every row to its nearest center\n3. Calculate a new center for each group based on all the rows assigned to it\n4. Repeat steps 2-3 until the centers stop moving (convergence)\n\n**Survey example:** You survey 1,000 customers on numeric scales: overall satisfaction (1-10), likelihood to recommend (1-10), and price sensitivity (1-10). K-Means with k=3 might discover:\n- **Group 1 (center: 9.2, 8.8, 2.1)**: Highly satisfied, loyal, price-insensitive (premium segment)\n- **Group 2 (center: 5.5, 5.2, 6.8)**: Middle of the road on satisfaction, price-conscious (value segment)\n- **Group 3 (center: 3.1, 2.9, 8.4)**: Dissatisfied, likely to shop around, very price-sensitive (deal-hunters)\n\nThe algorithm moves those centers around until each customer settles with their nearest group.\n\n**When to use it:**\n\n- You want exactly 3, 5, or 10 clusters—no guessing\n- Your survey uses only numeric questions (1-10 scales, numerical values). Note: Opinion scales like Likert scales are treated as numeric\n- You want something fast and interpretable\n- Your customer segments should be distinct and roughly balanced\n\n**What it's good at:**\n\n- Pure numeric survey data with clear segment patterns (e.g., satisfaction profiles, usage intensity levels)\n- Speed: runs quickly even on surveys with 10,000+ respondents\n\n**Limitations:**\n\n- Only works with numeric columns. If you include categorical survey questions (industry, yes/no, single-select responses), those columns get filtered out\n- Assumes clusters are roughly equal size and round-shaped\n- Can struggle if your segments naturally have very different sizes\n- Sensitive to outliers (one respondent with extreme scores can skew things)\n\n---\n\n## Important Note: How Data Types Are Treated\n\n**Numeric data** includes:\n- Numbers (e.g., age, company size, revenue)\n- Opinion scales (e.g., 1-10 satisfaction, Likert scales, NPS scores)\n- Percentages, Currency\n\n**Categorical data** includes:\n- Single-select categories (e.g., \"Which industry?\", \"Yes/No/Maybe\")\n- Multi-select tags (e.g., \"Which features do you use?\")\n\nFor clustering:\n- **K-Means** works with numeric data only (opinion scales included)\n- **K-Medoids** works with both numeric and categorical\n- **HDBSCAN** works with both numeric and categorical\n- **Balanced HDBSCAN** works with both numeric and categorical\n\nSo if you have a 1-10 opinion scale question, it's treated as numeric and works with all four algorithms. If you have \"Select your industry,\" that's categorical and K-Means will filter it out.\n\n---\n\n## K-Medoids: The Robustness King\n\n**What it does:** K-Medoids is like K-Means' tougher cousin. Instead of using an average center point, it picks actual respondents from your data as cluster centers (called \"medoids\").\n\n**How it works (step by step):**\n\n1. Pick `k` actual respondents as starting medoids (using a smart algorithm)\n2. Assign every other respondent to their nearest medoid\n3. For each group, check if a different respondent would be a better representative (lower total distance)\n4. Swap out medoids if it improves the clustering\n5. Repeat steps 2-4 until no more beneficial swaps happen\n\n**Survey example:** You survey 500 SaaS customers with mixed questions: satisfaction (1-10), usage frequency (daily/weekly/monthly), company size (1-50 / 50-200 / 200+), and churn risk (high/medium/low). K-Medoids with k=4 might pick these actual respondents as medoids:\n\n- **Medoid A**: Sarah from TechCorp, satisfaction 9, daily user, 150 employees, low churn risk → *represents your power users*\n- **Medoid B**: Mike from StartupXYZ, satisfaction 6, weekly user, 25 employees, medium churn risk → *represents growing companies*\n- **Medoid C**: Elena from Enterprise Inc., satisfaction 7, daily user, 500+ employees, low churn risk → *represents large accounts*\n- **Medoid D**: James from SmallBiz LLC, satisfaction 4, monthly user, 10 employees, high churn risk → *represents at-risk customers*\n\nEvery respondent gets assigned to whichever medoid (real person) is most similar to them.\n\n**When to use it:**\n\n- Your survey has both numeric and categorical questions\n- You want robust results without extreme values pulling things off\n- You want to show stakeholders a \"typical\" respondent from each cluster (\"This is Sarah, our power user profile\")\n\n**What it's good at:**\n\n- Mixed survey questions: numbers + categories + opinions all work together\n- Robustness: real respondents as centers, so not skewed by extreme answers\n- Interpretability: \"Meet your key customer types\" becomes real people\n- Irregular segment shapes: handles naturally unbalanced customer types\n\n**Limitations:**\n\n- Slower than K-Means\n- Still requires you to pick `k` upfront\n- Still assumes segments are roughly balanced in size\n\n---\n\n## HDBSCAN: The Natural Explorer\n\n**What it does:** HDBSCAN automatically finds natural, density-based clusters without you specifying how many. It treats sparse outliers as \"noise\" and focuses on dense regions.\n\n**How it works (conceptually):**\n\n1. Build a k-nearest-neighbor graph: for each respondent, find their closest neighbors\n2. Estimate the \"density\" around each respondent (are they clustered with similar people or isolated?)\n3. Find regions of high density—areas where many respondents cluster together\n4. Mark sparse, isolated respondents as noise/outliers\n5. Group the dense regions into clusters\n\n**Survey example:** You survey 800 companies on attitudes to cloud migration: cost concern (1-10), security concern (1-10), innovation priority (1-10), existing cloud usage (%), and industry. HDBSCAN might naturally discover:\n\n- **Cloud-Ready Innovators** (200 respondents clustered together): Low cost concern, low security concern, high innovation priority, already 60%+ cloud-using tech/finance companies\n- **Cost-Conscious Pragmatists** (300 respondents): High cost concern, medium security concern, medium innovation priority, 20-40% cloud usage, mixed industries\n- **Security-First Enterprises** (180 respondents): Medium cost concern, high security concern, low innovation priority, 30-50% cloud, healthcare/finance heavily represented\n- **Outliers/Noise** (20 respondents): Scattered responses that don't fit any pattern—maybe early-stage or unusual hybrid approaches\n\nThe algorithm automatically discovers these 3 clusters (plus noise) without you telling it \"find 3.\"\n\n**When to use it:**\n\n- You're exploring survey data and don't know how many segments exist\n- You want to identify genuinely unusual respondents (the noise group)\n- You have any mix of data types in your survey\n\n**What it's good at:**\n\n- Finding the \"natural\" number of segments automatically\n- Identifying outliers and unusual respondents\n- Handling segments that naturally vary in size\n- Mixed survey data: numbers, categories, opinions all work\n\n**Limitations:**\n\n- Slower than K-Means\n- If your `min_cluster_size` is too high, you might call real segments \"noise\"\n- Requires tuning: `min_cluster_size` affects how many respondents form a cluster\n- If respondents are very scattered, most might be marked noise\n\n---\n\n## Balanced HDBSCAN: The Best-of-Both-Worlds\n\n**What it does:** Combines HDBSCAN's smart outlier filtering with K-Medoids' balanced cluster sizes. It automatically finds natural survey segments, then refines them to be more even-sized.\n\n**How it works (step by step):**\n\n1. Run HDBSCAN to find natural customer segments and filter out true outliers\n2. Pick one representative respondent (medoid) from each natural segment\n3. Use K-Medoids to consolidate those representatives into exactly `k` final segments\n4. Assign all non-outlier respondents to the `k` segments, balancing sizes\n\n**Survey example:** You survey 1,200 B2B software customers on needs: budget size (numeric), decision-maker count (numeric), time-to-decision (numeric), industry (categorical), and product-market fit perception (categorical).\n\n**Step 1 (HDBSCAN finds natural clustering):** Discovers maybe 7 natural groups, but marks 30 weird responses as noise\n\n**Step 2 (Pick medoids):** Picks one \"representative customer\" from each of the 7 groups\n\n**Step 3-4 (Consolidate to balanced k=4):** Merges similar groups and assigns all 1,170 non-noise respondents into:\n\n- **Enterprise Buyers** (290 respondents): Large budgets, many decision-makers, long sales cycles, mostly Fortune 500\n- **Mid-Market Pragmatists** (280 respondents): Medium budgets, 3-5 decision-makers, mid-length cycles, diverse industries\n- **Fast-Growing Companies** (285 respondents): Growing budgets, fewer decision-makers, quick cycles, startups and scale-ups\n- **Cost-Conscious Small Teams** (315 respondents): Small budgets, 1-2 decision-makers, quick decisions, SMBs\n\nEach segment is balanced (~280-320 respondents) and represents a real, meaningful customer type.\n\n**When to use it (recommended default):**\n\n- You're analyzing survey data with mixed question types (recommended!)\n- You want clear, balanced customer personas (4-5 segments, not 2 or 12)\n- You want to ignore true outliers but keep borderline respondents\n- You need segments that are both natural and actionable\n\n**What it's good at:**\n\n- Survey data: the perfect fit for mixed numeric and categorical questions\n- Balanced personas: great for building 4-5 customer types for business strategy\n- Smart filtering: real outliers get marked as noise; unusual-but-real respondents still get segmented\n- Robustness: not sensitive to extreme individual answers\n\n**Limitations:**\n\n- Most complex (slower than K-Means)\n- If your data truly has very unbalanced natural segments, balancing will force artificial boundaries\n- Requires tuning for best results\n\n---\n\n## Quick Comparison Table\n\n| Aspect | K-Means | K-Medoids | HDBSCAN | Balanced HDBSCAN |\n|--------|---------|-----------|---------|------------------|\n| **Cluster count** | You specify `k` | You specify `k` | Auto-detected | You specify `k` |\n| **Data types** | Numeric only | All types ✓ | All types ✓ | All types ✓ |\n| **Speed** | Fast | Moderate | Slow | Slow |\n| **Robustness** | Sensitive to outliers | Robust | Robust | Robust |\n| **Outlier detection** | No | No | Yes (noise) | Yes (noise) |\n| **Balanced sizes** | Tends toward equal | Tends toward equal | Variable | Balanced ✓ |\n| **Best for** | Pure numeric surveys | Mixed surveys, show medoids | Exploration, outlier discovery | **Survey data (recommended)** |\n\n---\n\n## Choosing Your Algorithm\n\n**Start here:** Use **Balanced HDBSCAN** for survey data. It combines the best properties: robustness, mixed-data support, noise filtering, and balanced results.\n\nSee [Clustering](./clustering.md) to get started running your first clustering analysis. This guide has step-by-step instructions and tips on selecting columns and reviewing results.\n\n**Use K-Means if:**\n- All your survey questions are numeric (1-10 scales, numeric responses only)\n- You need to process a very large survey (50,000+ respondents) and speed matters\n- You want clean, distinct numeric profiles\n\n**Use K-Medoids if:**\n- Your survey has mixed questions (ratings + categories + opinions)\n- You want to show stakeholders actual respondent profiles (\"Meet your top 3 customer types\")\n- You want robustness without filtering outliers\n\n**Use HDBSCAN if:**\n- You're exploring survey data and don't yet know how many natural segments exist\n- You want to identify and remove survey noise (responses that don't fit any pattern)\n- You're okay with unbalanced segment sizes\n\n**Use Balanced HDBSCAN if:**\n- You're analyzing survey data (recommended!)\n- You want 3-5 balanced customer personas for business strategy\n- You want mixed survey questions handled naturally\n\n---\n\n## Tips for Better Results\n\n**Before you cluster:**\n- Include relevant survey questions: mix behavioral (frequency, usage) + attitudinal (satisfaction, priority)\n- Don't duplicate: if you asked \"overall satisfaction\" and \"overall satisfaction rescaled,\" include only one\n- Check data quality: extreme outlier responses can affect K-Means; balanced HDBSCAN filters them\n\n**After you cluster:**\n- Review the top features per segment—do they tell a coherent customer story?\n- Look at segment sizes—are they actionable? (If you get 5% and 95%, something's off)\n- If quality is \"Poor,\" try:\n - Different survey questions (maybe the ones you picked don't segment well)\n - A different algorithm\n - Adjusting `min_cluster_size` (higher = fewer, larger, more stable segments)\n\n**For business use:**\n- A \"Good\" quality score with clear, actionable personas beats \"Excellent\" with confusing segments\n- Test your segments: do they correlate with business outcomes (retention, upgrade, churn)?\n- Iterate: compare different question combinations and pick the version that best matches your business reality\n\n"},"stats/clustering":{"title":"Clustering","category":"Stats","slug":"stats/clustering","blurb":"Discover natural segments in your data by grouping similar responses using algorithms suited to mixed survey data.","order":7,"filename":"clustering.md","uid":"stats/clustering","content":"\n# Clustering\n\nClustering groups similar rows together to reveal natural segments (e.g., types of customers or respondent profiles). It works well for survey and behavioral datasets where you have a mix of Numbers, Single/Multi‑Category, and Opinion Scales.\n\n## Open the tool\n\n1. Click the **More** menu.\n2. Choose **Create clusters**.\n\nThis opens a panel where you pick the columns to include, choose an algorithm, and run clustering. After reviewing the results, you can add a calculated cluster column to your dataset.\n\n\n\n## How it works (quick version)\n\nClustering finds groups of rows that are more similar to each other than to the rest of the dataset. AddMaple offers multiple algorithms:\n\n- Balanced HDBSCAN (recommended): Works with mixed data types. Automatically balances cluster sizes while finding natural groupings.\n- HDBSCAN: Density‑based clustering that can detect outliers. Works with all data types.\n- K‑Medoids: Similar to K‑means but more robust to outliers. Works with all data types.\n- K‑Means: Classic algorithm for numeric data only (Numbers, Opinion Scales, Percentages, Currency).\n\nFor survey data with mixed categories and numbers, start with Balanced HDBSCAN.\n\n**Want more detail?** See [Understanding Clustering Methods](./clustering-methods-explained.md) for a deep dive into how each algorithm works and when to use it.\n\n## Step 1 — Select columns\n\nChoose the columns you want to use for clustering. You can include:\n\n- Numbers and Opinion Scales\n- Single Category and Multi Category\n\nTip: Include a balanced mix of behavioral and attitudinal variables. Remove obvious duplicates to avoid overweighting the same idea twice.\n\n## Step 2 — Choose algorithm\n\n- Balanced HDBSCAN (recommended): Works with Numbers, Single Category, and Multi Category. Best default for survey data. Balances cluster sizes automatically.\n- HDBSCAN: Finds density‑based clusters and marks outliers as noise. Works with all data types.\n- K‑Medoids: Requires you to specify the number of clusters. Works with all data types.\n- K‑Means: Requires you to specify the number of clusters. Only works with numeric columns (Numbers, Opinion Scales, Percentages, Currency).\n\nWhen you select K‑Means, incompatible columns are automatically filtered out.\n\n**Key choice:** Want exactly 3 clusters, or 5, or 10? Use K‑Medoids (works with any data type) or K‑Means (numeric data only). Both let you set the exact number upfront. Use the HDBSCAN variants when you want the algorithm to find the natural number of clusters automatically.\n\nFor detailed explanations of each method's strengths and limitations, see [Understanding Clustering Methods](./clustering-methods-explained.md).\n\n## Advanced options (optional)\n\nCommon settings across algorithms:\n\n- Number of clusters: For Balanced HDBSCAN and K‑Medoids/K‑Means, set how many groups you want. Balanced HDBSCAN can use \"Auto\" to detect the optimal number.\n- Min cluster size: Minimum rows required to form a cluster. Higher values produce larger, more stable groups (default: 50).\n\nEach algorithm has additional tuning parameters you can adjust for fine control. Most users should stick with the defaults.\n\nYou can reset to recommended settings anytime.\n\n## Run and review\n\nClick **Run Clustering**. You'll see:\n\n- Detected clusters (and a possible \"Noise\" group for outliers)\n- Each cluster's size and percent of rows\n- Top features per cluster to help explain what makes the group distinct\n\nHow to read features:\n\n- Numeric features show the cluster mean and a z‑score vs the dataset mean.\n- Categorical features show the percent in the cluster and a lift (×) vs overall.\n\n## Name and save clusters\n\nYou may see suggested names and descriptions for clusters to speed up labeling. When you're happy, click **Add Cluster Column** to add a new Single Category column to your dataset with the cluster labels. You can rename values later.\n\n## Understand cluster quality\n\nAfter running clustering, AddMaple shows you a **Quality** rating (Excellent, Good, Fair, or Poor). This helps you judge how well your clusters fit together.\n\nThe quality is determined by two statistical measures:\n\n**Silhouette Score** measures how well-separated your clusters are — how similar rows *within* each cluster are to each other, compared to rows *outside* that cluster.\n\n- 0.7+ = Excellent clustering (very tight, well-defined groups)\n- 0.5–0.7 = Good clustering (clear separation)\n- 0.2–0.5 = Fair clustering (some overlap; patterns are still meaningful)\n- <0.2 = Poor clustering (groups are scattered; reconsider your columns or algorithm)\n\n**PERMANOVA** is a statistical test that validates your clusters are genuinely different — not just random noise. It returns an R² value and a p-value:\n\n- R² > 0.5 = Strong separation (differences are substantial)\n- R² 0.3–0.5 = Moderate separation (differences exist but are smaller)\n- R² < 0.3 = Weak separation (very subtle or no real patterns)\n- p-value < 0.05 = Statistically significant (the clustering is real, not due to chance)\n\n**Why this matters:** Don't chase a perfect score. Fair results often capture real patterns. Poor quality suggests either that your columns don't cluster well together, or you need to adjust your algorithm settings. Try removing columns, adding more relevant ones, or switching algorithms.\n\n## History panel\n\nYour clustering runs are saved during your session, so you can compare different configurations and pick the best one.\n\n**Why use history:** Often the best insights come from iteration. You might:\n\n- Try different column combinations to see which creates the most meaningful segments\n- Switch between algorithms to find one that better captures your data patterns\n- Adjust parameters like Min Cluster Size to balance cluster granularity (many small groups vs. fewer large ones)\n- Compare quality scores across runs to pick the version that works best for your use case\n\n**How to access it:** Click the **History** button in the review screen. You'll see all runs from your current session, labeled with:\n\n- Run number (e.g., \"Run 2 of 5\")\n- Quality rating\n- Number of clusters and noise percentage\n- Algorithm used\n- Column count\n\n**Switching between runs:** Click any run to instantly reload its configuration and results. You can then:\n\n- Review its clusters and top features again\n- Modify settings and run a new iteration\n- Compare quality scores and cluster counts side-by-side mentally\n- Choose which result to add to your dataset\n\n**Note:** History resets when you close the clustering tool. To save a run permanently, add it as a column to your dataset.\n\n## Tips and limitations\n\n- Unsupervised insight: Clusters describe patterns; they aren't \"right or wrong\". Try different column sets and algorithms to find stable themes.\n- Rare categories can be noisy: Consider combining very small groups or increasing Min cluster size.\n- Algorithm choice: Use Balanced HDBSCAN for survey data. Use K‑Means when your inputs are all numeric and you want a fixed number of clusters. Use HDBSCAN when you want to identify outliers.\n- Don't over-optimize: A \"Good\" quality score with business-intuitive clusters beats an \"Excellent\" score with uninterpretable groups.\n\nAvailability: Clustering is limited to certain plans.\n\n\n"},"stats/correlation":{"title":"Correlation Tests (Pearson and Spearman)","category":"Stats","slug":"stats/correlation","blurb":null,"order":1,"filename":"correlation.md","uid":"stats/correlation","content":"# Correlation Tests (Pearson and Spearman)\n\nThese are run automatically when pivoting by 2 numeric columns. Pearson's correlation is applied if the data is normally distributed, while Spearman's correlation is used if the data is not normally distributed. These tests measure the strength and direction of the relationship between the two numerical variables. Learn more about [pivoting your data](../frequently-asked-questions/how-to-pivot-your-data).\n\n### Pearson's vs Spearman's\n\nIn this example the Pearson Correlation Coefficient was used as both of the columns were normally distributed. If one of them wasn't normally distributed then Spearman's rank correlation would be run. This happens automatically in AddMaple."},"stats/key-driver-analysis":{"title":"Key Driver Analysis","category":"Stats","slug":"stats/key-driver-analysis","blurb":"Learn how to find the factors that most influence your chosen outcome using AddMaple's Key Driver Analysis.","order":8,"filename":"key-driver-analysis.md","uid":"stats/key-driver-analysis","content":"\n# Key Driver Analysis\n\nKey Driver Analysis helps you discover which columns in your data most influence a chosen outcome. It works well for survey and behavioral datasets that mix numbers, opinion scales, and categories.\n\n## Open the tool\n\n1. Click the **More** menu.\n2. Choose **Find key drivers**.\n\nThis opens a panel where you pick an outcome, choose a model, and select candidate drivers. AddMaple will test likely relationships and run your chosen model to estimate each factor's impact.\n\n\n\n## How it works\n\nAddMaple offers two models:\n\n**Random Forest** — Trains many small decision trees that handle mixed data types and non‑linear patterns. Each factor is scored by measuring how much model accuracy drops when that factor is temporarily scrambled. Works best for categorical outcomes (e.g., Yes/No, satisfaction buckets, NPS groups).\n\n**Elastic Net** — A regression model that finds linear relationships between drivers and numeric outcomes. It assigns a coefficient to each driver showing direction and strength of impact. Works best for numeric outcomes (e.g., satisfaction scores, revenue, completion time).\n\n## Choosing a model\n\n**Use Random Forest when:**\n- Your outcome is categorical (Yes/No, NPS bucket, satisfaction level)\n- You have mixed data types (categories, scales, numbers)\n- You want to capture non‑linear patterns and interactions automatically\n- You don't need to interpret exact coefficients\n\n**Use Elastic Net when:**\n- Your outcome is numeric (satisfaction score, revenue, duration)\n- You want interpretable coefficients showing direction and magnitude\n- Relationships are roughly linear\n- You have primarily numeric or ordinal drivers\n\nAddMaple will automatically suggest compatible models based on your outcome type. You can switch models in the Configure step.\n\n## Step 1 — Choose an outcome\n\nPick one column you want to explain better. The outcome type determines which models are available:\n\n**For Random Forest:**\n- Opinion scales (Likert)\n- Single categories (e.g., NPS bucket, Yes/No, churned vs active)\n\n**For Elastic Net:**\n- Numbers (e.g., satisfaction score, time on task, revenue)\n- Opinion scales (Likert — treated as numeric)\n\nAvoid choosing an outcome that will be duplicated among the candidate drivers (data leakage).\n\n## Step 2 — Pick possible drivers\n\nAddMaple auto‑suggests columns that look related to your outcome. You can add or remove candidates freely. Useful drivers often include demographics, usage/behavior, attitudes, and experience ratings.\n\nSupported driver types include numbers, opinion scales, single categories, and multi‑select categories.\n\nTip: Very similar columns can share credit and split their importance. If you see near‑duplicates, consider choosing just one.\n\n## Step 3 — Configure and run\n\nChoose your model and adjust advanced options if needed. AddMaple will suggest compatible models based on your outcome type.\n\n### Advanced options (Random Forest)\n\n- **Number of trees**: More trees stabilize rankings but take a bit longer.\n- **Tree depth**: Limits how detailed patterns can get. Lower is simpler and safer.\n- **Features per split**: Fraction of drivers tried at each split to add variety and reduce bias.\n- **Minimum rows to split**: Smallest group size before the tree splits (helps smooth out noise).\n\n### Advanced options (Elastic Net)\n\n- **Alpha**: Controls the balance between Lasso (alpha=1, variable selection) and Ridge (alpha=0, shrinkage). Default 0.5 mixes both.\n- **Lambda**: Regularization strength. Higher values create simpler models with smaller coefficients.\n- **Standardize**: Whether to scale all inputs to the same range before fitting.\n- **Loss function**: How the model measures error. \"Auto\" picks based on your outcome type.\n\nYou can reset to recommended settings anytime.\n\n## Reading the results\n\nAfter you run the analysis, you'll see:\n\n- **Top drivers and summary**: A short description of what seems to move your outcome most\n- **Importance table**: Higher scores mean a factor explains more of the differences you see\n- **Model fit metric**: \n - For Random Forest: Out‑of‑bag balanced accuracy (how well the model predicts unseen rows)\n - For Elastic Net: R² score (how much variation in the outcome is explained)\n- **AI explanation**: An automatically generated interpretation of your results\n\n### Interpreting importance scores\n\n**Random Forest** — Importance scores show how much accuracy drops when each driver is scrambled. Higher values mean removing that driver hurts predictions more.\n\n**Elastic Net** — Importance scores are the sum of absolute coefficient values. They show total linear effect size. Positive coefficients increase the outcome; negative coefficients decrease it.\n\n### General tips\n\n- Results show associations, not strict causation. Use as directional guidance.\n- Very small categories can be noisy — consider combining rare groups or filtering.\n- Similar drivers may split importance between them.\n\n## Good to know\n\n- **Random Forest** works well with mixed data types and captures non‑linear patterns automatically. It's robust to outliers and missing values.\n- **Elastic Net** provides interpretable coefficients showing direction and magnitude of each driver's impact. Best for numeric outcomes with roughly linear relationships.\n- You can switch models and rerun to compare results\n- AddMaple automatically suggests columns that are statistically related to your outcome\n- AI-generated explanations help you understand what the results mean\n\nAvailability: Key Driver Analysis is limited to certain plans.\n\n\n"},"stats/kruskal-wallis":{"title":"How to run a Kruskal-Wallis test","category":"Stats","slug":"stats/kruskal-wallis","blurb":null,"order":6,"filename":"kruskal-wallis.md","uid":"stats/kruskal-wallis","content":"# How to run a Kruskal-Wallis test\n\nWhen you pivot by a categorical column and a numeric column, and the categorical column contains 2 or more categories with less than 4 results, AddMaple will use the Kruskal-Wallis test rather than ANOVA. \n\nFor the Kruskal-Wallis tests these are the outputs:\n\n- P-Value: the measure of probability as to whether the relationship between two columns is due to chance or not.\n\n- H Statistic: the value determines if there are significant differences among the distributions of groups. It compares the ranks of data across groups rather than the data values themselves. A higher H Statistic indicates that the differences among the groups are less likely to be due to random variation, suggesting stronger evidence against the null hypothesis that all groups have the same distribution\n\n- Eta-Squared: this indicates the strength of the relationship between categorical groups and numerical data. It shows what proportion of the total variance in the numerical data can be explained by the differences between the categorical groups."},"stats/nps":{"title":"Net Promoter Score","category":"Stats","slug":"stats/nps","blurb":null,"order":9,"filename":"nps.md","uid":"stats/nps","content":"# Net Promoter Score\n\nAddMaple will automatically calculate the Net Promoter Score (NPS) for columns that meet these criteria:\n\n1. The column has been detected as a Numeric Opinion Scale\n\n1. The values are between 0 and 10\n\nThis calculation happens automatically for you and is available via the stats tab.\n\n### NPS Calculations:\n\n**AddMaple automatically calculates the Net Promoter Score for you for questions with a 0 - 10 point scale **\n\n**Background and method:** Scroll down for how AddMaple helps calculate the NPS for you. \n\nNet Promoter Score (NPS) is a widely-used metric designed to gauge customer loyalty and satisfaction by measuring how likely they are to recommend a product or service to others.\n\n**How is NPS calculated?**\n\nRespondents are asked a single question: \"On a scale from 0 to 10, how likely are you to recommend [named product or service] to a friend or colleague?\" Based on their selections of this 11-point scale, customers are grouped into three categories:\n\n1. **Promoters** (scores of 9 or 10): These are your most satisfied and loyal customers who are highly likely to recommend your business.\n\n1. **Passives** (scores of 7 or 8): While generally satisfied, these customers are not enthusiastic enough to actively promote your business.\n\n1. **Detractors** (scores 0–6): These customers are dissatisfied and may spread negative opinions about your brand.\n\nThe NPS is calculated by subtracting the percentage of Detractors from the percentage of Promoters, yielding a score between -100 and +100. \n\n**Missing values are excluded:** If a row is missing an NPS score (blank / empty), AddMaple excludes it from the NPS calculation (it is not counted as 0).\n\n**NPS Scores can be interpreted as follows:**\n\n- **Below 0:** Very poor, most customers are dissatisfied. \n\n- **0 to 30:** Poor, there's room for improvement, as a relatively low percentage of customers are enthusiastic enough to recommend.\n\n- **30 to 70:** Good, this range generally reflects a healthy level of customer satisfaction and loyalty.\n\n- **Above 70:** Very good, indicating a strong, loyal customer base that is highly likely to recommend your business.\n\n**How To Get Automated NPS Calculations in AddMaple**\n\n**Tip: Check the NPS column 'type'** **first **\nEnsure that the NPS column is categorized as a pink Opinion Scale column type first. If the data wasn't detected correctly, use the pencil tool to correct it from the Chart Dashboard. You can follow this [user guide](../chart-dashboard/editcolumns) to edit column types. \n\nExpand a NPS column and then click the stats tab.\n\n\nOn the stats tab you will see the NPS calculation. Note that you don't need to group the responses into Promotor, Passives, Detractors in order for the calculations to take place. AddMaple does this for you. **To see a breakdown of the calculation hover over the (i) icon.**\n\n**How to see NPS calculations by segment:**\nAddMaple's NPS calculation will change depending on which filters you have applied. Which makes it easy to compare NPS calculations across segments, simply by clicking the **Filter** button at the top of the screen, and selecting which segment(s) you'd like to look at. You could also compare how responses to questions impact NPS scores. \n\n### NPS dot plots\n\nIf you pivot a category (like Gender) against an NPS score, AddMaple can show NPS results as a dot plot. See [Dot Charts](../pivot-chart-and-table/bubble-dot-plots) for how NPS dot plots scale (-100 to 100 fixed scale) and how auto scale works.\n\n**What is statistically correlated to the NPS categories? **\nAddMaple automates correlation analysis for you. To see which variables or questions are significantly related to the NPS categories to reveal patterns in between whether a respondent was a 'Promotor', Detractor', 'Passive' bucket, you can use the automated stats engine. You can also analyze the text column linked to this question, to find common themes belonging to each of these NPS categories. \n\nFor this, you will need to create three category buckets using the 'Segment and Merge' feature under Options. You will also need to analyze the text column into thematic categories. Once you've done this, you can pivot the thematic category columns with the NPS column you created to see the spread of themes by NPS category. \n\n \n"},"stats/regression":{"title":"Regression","category":"Stats","slug":"stats/regression","blurb":null,"order":2,"filename":"regression.md","uid":"stats/regression","content":"# Stats\n\n### Regression\n\nYou can perform linear regression and logistic regression in AddMaple.\n\nTo get started click the More menu and selection \"Regression Analysis\"\n\n\nA pop up box will appear where you can choose the columns to perform the regression on. Currently we support linear and logistic regression between numeric columns and binary columns (either a boolean column or a multiple choice column with 2 categories).\n\nWe are planning to add support for multivariate regression soon.\n\n\nIf you select 2 numeric columns and click Compute Regression, AddMaple will performa linear regression. The results of the linear regression are shown together with an interpretation. \n\n\nBelow the numeric results you will find a scatter plot with the line of regression.\n\n\nBy default AddMaple will hide outliers. You can toggle them on to view the full dataset.\n\n\nTo perform a logistic regression, select a numeric column and a binary column (either a boolean or a multiple choice column with 2 categories).\n\nAddMaple will show you the Log Odds Ratio, Intercept and Pseudo R-Squared results, along with an interpretation.\n\n\nBelow the results there will be a chart showing the regression curve.\n\n\n### Save your findings\n\n- Use **Save to Insights** on the review screen to capture the full regression snapshot—metrics, ranked drivers, and AI guidance—without rerunning the model.\n- Pick **Add to Dashboard** to drop the same card onto any dashboard page so stakeholders can monitor the drivers alongside their other charts.\n- Saved analyses reopen instantly: click the item in Insights (or on the dashboard) and AddMaple restores the stored results plus the original configuration.\n"},"stats/related-columns":{"title":"Exploring Related Columns","category":"Stats","slug":"stats/related-columns","blurb":"Discover statistically significant relationships between your columns and understand why some relationships might not appear.","order":10,"filename":"related-columns.md","uid":"stats/related-columns","content":"# Exploring Related Columns\n\nAddMaple automatically analyzes your data to find statistically significant relationships between columns. When you select a column, AddMaple tests it against all other columns in your dataset using appropriate statistical tests.\n\n## How It Works\n\nAddMaple performs different statistical tests depending on the data types:\n\n- **Categorical vs Categorical**: Chi-square test with Cramer's V effect size\n- **Numeric vs Categorical**: ANOVA (for 3+ groups) or T-test (for 2 groups) with Cohen's d effect size \n- **Numeric vs Numeric**: Pearson correlation (for normal data) or Spearman correlation (for non-normal data)\n\nResults are ordered by statistical significance and effect size, showing you the strongest relationships first.\n\n## Viewing Related Columns\n\nIf AddMaple detects columns that are significantly related to your selected column, they will show up in the **Stats** tab:\n\n\n\nThe results are ordered by significance. Click on any column to automatically create a pivot chart showing the relationship.\n\n\n\n## Understanding Statistical Results\n\nWhen you are viewing 2 columns pivoted together, AddMaple automatically shows a **Stats Overview** card that summarizes the relationship strength at a glance. This card uses color coding (green for strong relationships, orange for moderate, gray for none) and provides a plain-English interpretation of the statistical results.\n\nYou can also analyze relationships directly in pivot tables using [significance testing](significance-testing), which highlights cells with z-score shading to show where segments perform higher or lower than expected. \n\n\nIn the \"stats\" tab, click the toggle **\"Statistical Test and Calculations\"** to see the detailed calculations behind each result. This shows you:\n\n- The specific statistical test used (Chi-square, ANOVA, T-test, or correlation)\n- P-value (statistical significance)\n- Effect size measures (Cramer's V, Cohen's d, or correlation coefficient)\n- Sample size and degrees of freedom\n\nClick the toggle **\"Further Insights Between Column Categories\"** to discover which specific groups are most significantly different from the rest. This detailed breakdown only appears for chi-square and ANOVA comparisons.\n\n\n\n## Why You Might See Few or No Related Columns\n\nIf AddMaple finds few or no statistically significant relationships, this could be due to several factors:\n\n### Insufficient Data\n- **Small sample size**: Statistical tests require adequate data to detect relationships\n- **Low counts**: Category pairs with very few responses (expected counts less than 5) tend to reduce statistical significance \n- **Missing data**: High amounts of missing or empty values reduce the effective sample size\n\n### Data Characteristics\n- **Uniform distributions**: If most categories have similar response patterns, relationships may not be detectable\n- **Weak relationships**: Some relationships exist but are too weak to reach statistical significance\n- **Data quality**: Inconsistent or unclear category definitions can mask real relationships\n\n### Statistical Thresholds\n\nAddMaple uses conservative statistical criteria:\n- P-value must be less than 0.05 (95% confidence level)\n- Effect sizes must meet minimum thresholds for practical significance\n- At least 80% of contingency table cells must have expected counts ≥ 5\n\n"},"stats/significance-testing":{"title":"Significance Testing","category":"Stats","slug":"stats/significance-testing","blurb":"Highlight meaningful differences between segments with z-score shading, Holm-adjusted tiers, and practical effect guards.","order":12,"filename":"significance-testing.md","uid":"stats/significance-testing","content":"# Significance Testing\n\nAddMaple can highlight where a segment is performing higher or lower than expected in any pivot table that compares two categorical groupings (including multi-select tags). We run z-score based significance tests for every cell so you can see which intersections are worth a second look without exporting to a separate stats package.\n\n### Turn on significance shading\n\n1. Build the table you want to analyze. Significance is available for stacked tables with at least two segment columns and more than one category per axis.\n2. Open the chart actions menu (the three-dot **More** menu) and toggle **Significance Testing**.\n3. We automatically switch the table into percentage view (`% of column`) so you can compare segments on the same base size. Count view is disabled while significance is on.\n4. A legend appears underneath the table explaining the colors that are now applied to the cells.\n\n### Read the colors\n\n- Warmer shading means the observed share for that segment is **higher** than expected; cooler shading means it is **lower**.\n- The deeper the color, the stronger the effect size (Cohen's *h*). Neutral (white/grey) cells show no statistical signal.\n- Hover any colored cell to see a tooltip with the z-score, Holm-adjusted p-value, effect size (Cohen's *h*), and expected baseline percentage.\n- We use the same color settings as set for Opinion Scales. Learn how to customize these colors [here](../preparation/colors).\n\n### How the coloring works\n\nAddMaple uses two visual signals:\n\n- **No color** (white/grey): Holm-adjusted p-value > 0.10 — no clear signal\n- **Circle marker** (faint color): Holm p-value between 0.05 and 0.10 — marginal signal (interesting hint, but not statistically strong)\n- **Background shading** (solid color): Holm p-value ≤ 0.05 — statistically significant. The color intensity reflects the effect size (Cohen's *h*): stronger effects get darker shading\n\nFor multi-select columns, the same thresholds apply; significance is calculated at the overlap level.\n\n### Why colors don't change when you switch \"% of column / % of row / % of all\"\n\nSignificance is computed from the raw contingency counts, which don't change when you change how the table displays percentages. Switching the displayed denominator only changes the formatting of the numbers, not the underlying counts or the chi-square residuals — so the z-scores (and therefore colors) stay the same.\n\n### What the tiers mean\n\nAddMaple places each cell into one of three p-value brackets:\n\n- **No clear signal** (p > 0.10): Holm-adjusted p-value above 0.10. These cells remain uncolored. They may be real patterns but don't meet the confidence threshold.\n- **Marginal signal** (0.05 < p ≤ 0.10): Cells marked with a faint circle. These are interesting hints—worth a second look—but not yet statistically convincing after correction for multiple comparisons.\n- **Statistically significant** (p ≤ 0.05): Cells with background shading. These pass the Holm-adjusted significance threshold. The *depth* of shading reflects effect size (Cohen's *h*): larger differences get darker colors.\n\nThe practical effect size (≥ 5 percentage points or h ≥ 0.20 for multi-select) is baked into the backend calculations and helps determine which cells are worth investigating, but all cells that meet the p ≤ 0.05 threshold will be shaded.\n\n### How we calculate it\n\n- We build a contingency table of the two pivoted columns and run a chi-square test.\n- Each cell's color is based on its Holm-adjusted p-value and effect size (standardized residual / Cohen's *h*).\n- We correct p-values within each column using Holm-Bonferroni so repeated comparisons stay statistically conservative.\n- Color intensity (darkness) is proportional to effect size: larger Cohen's *h* values produce darker shading for p ≤ 0.05 cells.\n- Numeric vs categorical pivots (e.g. scalar scores against segments) still generate the same chi-square contingency table behind the scenes, so the z-scores remain comparable.\n\n### Tips & limitations\n\n- Significance only appears when every column has more than one category and the table is not filtered down to a single row or column.\n- Charts keep significance on when you swap between pivoted table and chart views, but we only color the table itself.\n- Turning the toggle off restores your previous count/percentage settings.\n- Combine with filters to focus on segments with enough responses before trusting the directional hints.\n- If you apply respondent weights in the pivot builder, those weights flow into the contingency counts and z-scores, so the shading and tiers reflect the weighted contribution of each response.\n\nWith significance testing enabled you can scan for reliable lifts or drop-offs in seconds, then dive into the supporting rows or excerpts to understand *why* those differences exist.\n"},"stats/ttest":{"title":"How to run a T-Test","category":"Stats","slug":"stats/ttest","blurb":null,"order":3,"filename":"ttest.md","uid":"stats/ttest","content":"# How to run a T-Test\n\nAddMaple performs a 2-sided T-Test automatically when you pivot by a numeric column and a categorical column with only 2 categories. If you want to run a T-Test on a column with more than 2 categories, you first need to filter down to only look at 2 categories.\n\nTo get started, pivot by the 2 columns. For example in this diabetes prediction dataset we've pivoted by hypertension (category: 1 or 0) and BMI (numeric)\n\n\nThe summary of the t-test will be shown in the legend. To see the numbers behind the t-test click on the \"See More\" link. This will take you to the stats column where we have more details.\n\n\nThe narrative explains the results of the T-Test. In this particular example there is a significant relationship between Hypertension and BMI with a moderate effect size. The numeric results of the test are below the text summary.\n"},"table/addfiltertable":{"title":"Adding a filter from the table view","category":"Table","slug":"table/addfiltertable","blurb":"Add a filter by clicking a value in any table cell, then continue exploring with the filtered rows.","order":3,"filename":"addfiltertable.md","uid":"table/addfiltertable","content":"# Table\n\n### Adding a filter from the table view\n\nYou can add a filter by clicking on the value that you would like to filter by in the table. For example when viewing an \"Age\" column, clicking on the \"65+\" value from one of the rows will filter the entire table to only show rows where the \"Age\" is \"65+\".\n\n\n"},"table/addremovetablecol":{"title":"Adding and removing columns in the table view","category":"Table","slug":"table/addremovetablecol","blurb":"Add or remove columns using the multi-select box; quickly add many with Select All or clear them entirely.","order":2,"filename":"addremovetablecol.md","uid":"table/addremovetablecol","content":"# Adding and removing columns in the table view\n\nThis is done via the multi select box in the sentence builder.\n\nTo **add a single** column, either scroll to find the column or type to find it. Once your column is selected either click on it or press \"enter\" to add it to the table view.\n\n\n\nTo **add multiple** columns at once, use the text box to search and find the columns you want to add, and then click \"select all\".\n\n\n\nTo **remove a single** column, find the column you want to remove and click it or press \"enter\".\n\n\n\nTo **remove all** columns, click the \"clear all\" option in the bottom left.\n\n"},"table/explorerow":{"title":"Exploring a single row","category":"Table","slug":"table/explorerow","blurb":"Open a single record to read its values and compare them to the overall dataset.","order":4,"filename":"explorerow.md","uid":"table/explorerow","content":"# Exploring a single row\n\nTo explore a single row, simply click on the row number (in the left column)\n\n"},"table/sorttable":{"title":"Sorting table columns","category":"Table","slug":"table/sorttable","blurb":"Sort any table column by clicking its sort icon; click again to toggle direction.","order":1,"filename":"sorttable.md","uid":"table/sorttable","content":"# Sorting table columns\n\nAll columns in the table view are sortable. Simple click on the sort icon next to the column title. Clicking again will toggle between ascending and descending order. You can also [add or remove columns](../table/addremovetablecol) from your table view.\n\n \n\n\n\n![\"image\"](\"https://github.com/user-attachments/assets/c838112f-5f50-4a1c-9491-14c49b5a4f5e\")
\n"},"text-analysis/addcodes":{"title":"Adding Codes","category":"Text Analysis","slug":"text-analysis/addcodes","blurb":null,"order":1,"filename":"addcodes.md","uid":"text-analysis/addcodes","content":"# Adding Codes\n\nAfter you've created a new column with thematic codes, you can add or edit codes via the table view. Learn more about [creating coded columns](../text-analysis/ai-codes) and [manual code editing](../text-analysis/manual-code-editing).\n\nFrom the chart view for a coded column, click \"View text and codes\"\n\n\nThis will take you to the table view where you can see the text column along side the thematic codes. \n\nThe text highlights show which code has been applied to which section of the text.\n\nTo remove a code from a text record, simply hover over the code and click the trash icon.\n\n\nTo add a new or existing code, select the relevant portion of text and a pop-up box will appear. \n\nFrom this box you can choose an existing code, or add a new code.\n\n\nIf you've manually added new codes and want AddMaple's AI engine to apply them across the rest of your column, simply return to the chart view for your thematic codes and click \"Use AI to apply new codes.\"\n\n\nThis will take you to a screen where you can choose how to reapply:\n\n- **Apply new codes** (only the codes you just added), or\n- **Catch up uncoded rows** (apply all codes, but only to rows that have no codes yet).\n\nRest assured, AddMaple won't edit your existing codes, this workflow simply adds new codes to rows where they are relevant.\n"},"text-analysis/ai-codes":{"title":"How to analyze text data thematically or categorically with AI","category":"Text Analysis","slug":"text-analysis/ai-codes","blurb":null,"order":2,"filename":"ai-codes.md","uid":"text-analysis/ai-codes","content":"# How to analyze text data thematically or categorically with AI\n\nBelow is a guide for how to work with an AI research Co-Pilot to analyze text. \n\nAnalyzing text with AddMaple's AI Co-Pilot is built to follow the same process as working without AI or collaborating with a human research partner. \n\n**The process in brief is described below:**\n\nWhen analyzing text, we read the text data and decide on codes or categories to group the text records into. From there we might refine the codes, merge a few, get rid of some, add new codes and then apply the new codes to all records. You can use AddMaple's AI co-pilot achieve this. \n\n**This guide takes you through the steps to analyze text by coding text records with AI:**\n\n- Set up & getting started\n\n- Generate codes with AI or add your codes \n\n- Refine codes and apply them to individual records with AI\n\n- Review the analysis, add & remove codes to records as necessary\n\n- Use AI to apply newly added codes to the rest of the records\n\n- Explore statistical Insights\n\n- Share and export your findings\n\nTo analyze text, you need to find the column containing the text data using the search bar on the dashboard. Check that it is detected as a **Text** column. \nSee the tip below for what to do if it isn't. Click on the chart to expand it. \n\nWhen you expand a text column, you will see an Interactive Word Cloud. To analyze the text data you need to click on **✨AI Coding / Tagging**\n\n\n### Tip: Changing the column type to 'text'\n\nIf your text column isn't automatically detected as a text column, you need to first change the 'column type' from the Chart Dashboard. [See here for details on how to do that.](../chart-dashboard/editcolumns) Why does AddMaple occasionally show text columns as a 'multiple choice' columns? This is to automatically show you duplicates in the text data, highlighting potential copy/paste responses to help you detect potentially fraudulent or fake entries during cleaning. Also we pull out those mid dot responses!\n\nThe start screen for AI text analysis \n\n\nNext you can choose whether to use your own codes or to let our AI generate codes for you. Using your own codes is useful for when you have an existing codebook you've used for a previous project.\n\n\nIf you choose \"Get codes with AI,\" you'll be taken to a screen where you can guide our AI on the type of codes you'd like to generate. Enter your custom instructions in the white box, or select one of the suggested prompts on the right.\n\nWhile this step isn't mandatory, it can be helpful in ensuring the generated codes align with your research question. For example, you might want to focus only on bugs or extract all the brands mentioned.\n\n**Tip**: AI-generated codes will include descriptions and examples that you can refine in the next step. These help improve accuracy when applying codes - descriptions clarify when to use each code, while verbatim examples ground the AI in your actual data language.\n\nWith AddMaple, you can create multiple analysis columns from a single text column. This flexibility is especially useful when coding a column from different perspectives to get richer insights.\n\nOn this screen, you can also specify the number of codes you'd like to generate. Choosing a smaller number, such as 5, will produce broad themes, while selecting a higher number, like 30, will generate more detailed, fine-grained codes.\n\nWhen you are happy with your settings, click \"Generate with AI\".\n\n\nIf you choose the \"I have codes\" option, you will be taken to this screen where you can type or paste in your existing codes. \n\nYou can enter up to 50 codes - each should be on it's own line. \n\nWhen you are ready, click \"Continue\" and you will be taken to the review page where you will still have a chance to edit your codes before applying them to your data.\n\n\nOnce your codes have been generated (or manually added), you can review and refine them.\n\nGenerated codes now include **descriptions** and **examples** that you can edit to improve accuracy:\n\n- **Code Title**: Edit the name of the code (keep it to 5 words or less)\n- **Code Description**: Add a 1-3 sentence description to clarify when to apply this code\n- **Verbatim Examples**: Include short example snippets from your actual data to ground each code in real user language\n\nYou can also **merge** similar codes, **delete** any that aren't relevant, or **add new codes** by clicking \"Add code.\"\n\nAfter refining your codes, name your analysis column. We'll suggest a name based on your codes, but you can edit it or keep the suggested one.\n\nFinally, choose the type of operation:\n\n- **Apply One Code Per Record: **For categorical operations, e.g. sentiment analysis\n\n- **Apply Multiple Codes per Record**: For thematic coding operations - you can also set a maximum number of codes per record.\n\n\nTo merge codes:\n\n1. Select the codes to merge (you can hold down shift to select multiple codes in one go)\n\n1. Click the \"Merge Selected\" button\n\n1. Select the name to use for the merged codes (you can use one of the existing names or enter a new name)\n\n1. Click \"Save\"\n\n\nOnce you're satisfied with these settings, click **\"Apply Codes\"** to complete the process.\n\nWe'll now start applying your codes to each record, which may take anywhere from 5 seconds to 5 minutes depending on the number of records.\n\nYou can close the pop-up and continue using AddMaple while this process runs in the background, or wait for the results to complete.\n\n\nOnce coding is complete, you'll see a summary of the results. From there, you can choose to either explore the counts of each code in our pivot chart or review the data row by row, with highlighted text showing where each code was applied.\n\n\nEach time you perform an AI Coding operation, we will create a new column for your results. You can explore this column, like any other in AddMaple.\n\nThis is the Pivot Chart view and from here you can:\n\n1. View a Pivot Table\n\n1. [Pivot by another column](../sentence-builder/addpivot)\n\n1. Get an [AI Explanation](../pivot-chart-and-table/explain-chart)\n\n1. View [related columns](../stats/related-columns)\n\n1. Rename, merge or delete codes\n\nTo view how the codes were assigned row by row, click the \"View text and codes\" button on the left.\n\n\nIn this view you can explore how AddMaple has assigned codes to each text record.\n\nAddMaple highlights the relevant section of the text response that relates to the assigned code. \n\n\nTo add a code, simply select the relevant text and a pop up box will appear. Select an existing code, or enter a new code, then click \"Add Code\". \n\n\nTo delete a code from a text record, hover over the code and click on the trash icon. The code will now be removed from that particular record.\n\nYou can delete a code from all records (or merge it with another code) from the chart view.\n\n\nIf while reviewing the text and codes, you discover that there is a missing code you don't need to manually assign it to all your records. You can head back to the chart view by clicking the chart icon at the top of your coded column and use AI to apply your new codes to the rest of your records.\n\nYour existing codes won't be changed. AddMaple will either:\n\n- **Apply your new codes** across the rest of the dataset (only the newly added codes), or\n- **Catch up uncoded rows** (apply all codes, but only to rows that have no codes yet).\n\nBoth options are designed to preserve the manual work you've already done.\n"},"text-analysis/ai-models":{"title":"AI Models","category":"Text Analysis","slug":"text-analysis/ai-models","blurb":null,"order":4,"filename":"ai-models.md","uid":"text-analysis/ai-models","content":"# Text Analysis\n\n### AI Models\n\nFor [thematic coding](ai-codes) you can choose among three models when applying codes.\n\n- **Fast** — Best for quickly tagging broad themes and sub-themes. Use when you need efficient coding on large volumes of text (e.g. “Common themes in reasons for patient visits” or “Main topics in open-ended survey responses”).\n\n- **Deep** — Best for more nuanced analysis and sentiment. Use when you care about tone, polarity, or specific topics (e.g. “Extract food mentions in restaurant reviews and code by sentiment to see most/least praised foods” or “Identify and code positive vs negative feedback themes”).\n\n- **Deep + Web** — Same as Deep, plus optional web search so the model can use up-to-date or niche context when it helps (e.g. distinguishing an artist from an event, or coding current or specialized topics). Slower and uses more credits than Deep.\n\nAll models support multi-language analysis (80+ languages).\n\nWhen you apply codes, you choose the model in the dialog; AddMaple will show an estimate of credits based on the amount of text you’re analyzing. \n\n"},"text-analysis/ai-summary":{"title":"AI Summaries of Text Columns","category":"Text Analysis","slug":"text-analysis/ai-summary","blurb":null,"order":3,"filename":"ai-summary.md","uid":"text-analysis/ai-summary","content":"# AI Summaries of Text Columns\n\nWhen viewing a text column, you will see a button: **Get AI Summary**\n\nClick this button and we will start creating an AI summary of all your data. \n\nIf your data has about 20,000 words, then your summary will be returned right away:\n\n\n\n\nFor larger datasets, AddMaple will take some time (from 30 seconds to an hour depending on the size of the data). To speed up processing, you can filter your dataset in AddMaple and request a summary for just your filtered data.\n\nOnce the processing has been completed you will receive an email and will be able to view the summary from the **My Insights** section of your project.\n\n\n\n\n## Ask follow-up questions\n\nAfter your initial summary is ready, you can ask follow-up questions directly from the summary view:\n\n- Use the input labeled \"Ask a follow-up…\" at the bottom of the results\n- Click **Ask** to submit your question\n- Each reply will be added below the summary and labeled as \"Follow-up 1\", \"Follow-up 2\", etc.\n\nFollow-ups use the same context as your original summary, so you can drill into specific topics (e.g. \"Which themes were most common among detractors?\"). You can also click **← Edit Prompt** to change the original instruction and regenerate the summary if you want to take the analysis in a new direction.\n\nThe **Copy**, **Word Doc**, and **Save** actions include any follow-up answers that appear in the results."},"text-analysis/clean-mentions":{"title":"Merging Similar Categories (e.g. Mentions)","category":"Text Analysis","slug":"text-analysis/clean-mentions","blurb":null,"order":5,"filename":"clean-mentions.md","uid":"text-analysis/clean-mentions","content":"# Merging Similar Categories (e.g. Mentions)\n\nAnalyzing open-ended survey responses, such as brand, product, or artist mentions, can be challenging due to variations in spelling and phrasing. With AddMaple's \"Merge Similar Mentions\" feature, you can clean and organize this data in seconds.\n\nSimply select the relevant columns, and AddMaple will automatically identify and suggest groups of similar mentions for you to merge. \n\nFrom the More menu select **\"Merge Similar Mentions\"**\n\n\nA pop-up box will appear to guide you through the flow\n\n\nThe first step is to select the columns containing the categories or mentions you want to merge. You can choose one column or multiple columns.\n\nIf you can't see your column, make sure it is either a **Multiple Choice** or **Multi Select** column. If it's been detected as a text column, you will first need to change the type.\n\nSelecting multiple columns has the advantage of ensuring consistency across them. AddMaple will align similar mentions across all selected columns, making it easier to group them together later. This process won't create a new column—it simply merges the mentions or categories you confirm.\n\n\n### Choosing the best column type\n\nAddMaple automatically detects column types based on your data - these are correct 99% of the time.\n\nOccasionally we may not detect the correct column and you will need to change the column type. This happens more frequently with \"mentions\" data. Sometimes we detect it as free text - whereas for this flow to work it needs to be either \"Multiple Choice\" or \"Multi Select\".\n\nIf your column contains multiple mentions in a single row, for example someone may enter \"Apples, Oranges, Bananas\" then be sure to change the type to \"Multi Select\".\n\nYou can change the type of a column from the chart dashboard - see this guide [here](../chart-dashboard/editcolumns)\n\n On the next screen, you'll see two types of merge groups. The first type highlights groups with multiple variations. You can choose to \"Confirm All\" to approve all suggested groups at once or review each group individually.\n\nTo edit a group, click the pencil icon. This allows you to:\n\n1. Change the merge name.\n\n1. Add or remove categories/mentions within the group.\n\nOnce you're satisfied with a group, click the \"Confirm\" button on the right to finalize it.\n\n\nThe second type of merge groups includes items where the only differences are in capitalization. These groups are automatically confirmed for your convenience, but you can choose to unconfirmed and edit them if needed.\n\nWhen you are ready to proceed click \"Review Codes\"\n\n\nYou'll then see a screen displaying all your confirmed groups. From here, you can remove groups, return to the review stage for further edits, or click \"Confirm Merges\" to apply your changes.\n\nOnce the merges are applied, your mentions will be consolidated, allowing you to seamlessly continue exploring and analyzing your data in AddMaple.\n"},"text-analysis/manual-code-editing":{"title":"Manual Code Editing and Management","category":"Text Analysis","slug":"text-analysis/manual-code-editing","blurb":"Learn how to manually add, edit, and delete codes on individual text records after AI analysis","order":6,"filename":"manual-code-editing.md","uid":"text-analysis/manual-code-editing","content":"# Manual Code Editing and Management\n\nAfter completing AI text analysis and creating a coded column, you can manually review, add, edit, and delete codes on individual text records. This allows you to refine the AI's work and ensure accuracy in your analysis.\n\n## Accessing the Manual Editing Interface\n\n### From Chart View\n1. After AI coding is complete, you'll see your coded column in chart view\n2. Click **\"View text and codes\"** button on the left side of the screen\n3. This switches you to table view where you can see both the original text and applied codes\n\n\n\n### Understanding the Table View\nIn table view, you can see:\n- **Original text column**: The source text data\n- **Coded column**: Shows which codes have been applied\n- **Highlighted text**: Color-coded sections showing exactly where each code was applied\n- **Code tags**: Visual indicators showing which codes are assigned to each text segment\n\n\n\n## Adding Codes to Text\n\n### Adding Codes to Specific Text Segments\n1. **Select text**: Click and drag to highlight the relevant portion of text in any record\n2. **Choose action**: A popup will appear with options to:\n - **Apply existing code**: Choose from your existing codes\n - **Create new code**: Enter a new code name\n3. **Confirm**: Click \"Add Code\" to apply your selection\n\n\n\n### Tips for Adding Codes\n- Select the most relevant text snippet that represents the code\n- You can apply multiple codes to overlapping or different parts of the same text record\n- New codes you create will be available for the entire column, not just the current record\n\n## Removing Codes\n\n### Removing Codes from Individual Records\n1. **Find the code tag**: Locate the code you want to remove in the table view\n2. **Hover over the code**: A trash icon will appear\n3. **Click the trash icon**: The code will be removed from that specific record only\n\n\n\n### Managing Codes Globally\nTo remove or merge codes across your entire dataset:\n1. Return to **chart view** by clicking the chart icon\n2. Use the legend management tools to:\n - **Delete codes** from all records\n - **Merge similar codes** together\n - **Rename codes** for clarity\n\n## Applying New Codes with AI\n\nIf you've manually added new codes and want AI to apply them to the rest of your dataset:\n\n1. **Return to chart view** from the table view\n2. **Click \"Use AI to apply new codes\"** \n3. **Choose how to reapply**:\n - **Apply new codes** (only the codes you just added), or\n - **Catch up uncoded rows** (apply all codes, but only to rows that have no codes yet)\n4. **Let AI work**: AddMaple will analyze your data and apply the new codes where relevant\n\n\n\n**Important**: This process is designed to preserve your manual work. It only adds codes where relevant, and does not remove or overwrite existing coding.\n\n\n\n## Best Practices for Manual Coding\n\n### Quality Control\n- **Review AI suggestions**: Check that automatically applied codes make sense in context\n- **Be consistent**: Apply similar codes to similar concepts across your dataset\n- **Use specific text selection**: Highlight the exact words or phrases that represent each code\n\n### Workflow Efficiency\n- **Start with AI**: Let AI do the bulk of the coding work first\n- **Focus on edge cases**: Manually review records where AI might have struggled\n- **Iterate gradually**: Make small corrections rather than wholesale changes\n- **Use AI re-application**: When you add new codes, let AI help apply them broadly\n\n### Code Management\n- **Keep codes focused**: Each code should represent a distinct concept or theme\n- **Use clear names**: Make code names descriptive and unambiguous \n- **Merge similar codes**: Combine codes that represent the same concept\n- **Document your process**: Keep notes about your coding decisions for consistency\n\n## Troubleshooting\n\n### If you can't see the manual editing interface:\n- Make sure you're viewing a coded column (created through AI analysis)\n- Click \"View text and codes\" from the chart view\n- Ensure you have the necessary permissions to edit the data\n\n### If codes aren't applying correctly:\n- Check that you've selected the right text segment\n- Verify the code name doesn't conflict with existing codes\n- Try refreshing the page if the interface becomes unresponsive\n\n### If AI re-application isn't working:\n- Ensure you've created at least one new code manually\n- Check that you have sufficient credits for AI processing\n- Return to chart view before attempting to use AI features\n\nBy combining AI efficiency with manual precision, you can create highly accurate and nuanced text analysis that meets your specific research needs.\n"}}