Inspect a View using Explain Data
Explain Data gives you a new window into your data. Use it to inspect, uncover, and dig deeper into the marks in a viz as you build, explore, and analyze your data. When you select a mark while editing a view and run Explain Data, Tableau builds statistical models and proposes possible explanations for the selected mark, including potentially related data from the data source that isn't used in the current view.
As you build different views, use Explain Data as a jumping-off point to help you explore your data more deeply and ask better questions.
Creators and Explorers with editing permissions can use Explain Data when editing a view in Desktop, or editing a view on the web in Tableau Online or Tableau Server. The data must be drawn from a single, primary data source. Explain Data does not work with blended or cube data sources.
Note: Explain Data is a tool that uncovers and describes relationships in your data. It can't tell you what is causing the relationships or how to interpret the data. You are the expert on your data. Your domain knowledge and intuition is key in helping you decide what characteristics might be interesting to explore further using different views. For more information, see How Explain Data Works and Requirements and Considerations for Using Explain Data.
For related information on how Explain Data works, and how to use Explain Data to augment your analysis, see these Tableau Conference presentations:
- From Analyst to Statistician: Explain Data in Practice (1 hour)(Link opens in a new window)
- Leveraging Explain Data (45 minutes)(Link opens in a new window)
- Explain Data Internals: Automated Bayesian Modeling (35 minutes)(Link opens in a new window)
- Machine Learning, Explainable AI, and Tableau (45 minutes)(Link opens in a new window), Session Materials
- Making Business More Bayesian (45 minutes)(Link opens in a new window)
Steps to use Explain Data
To use Explain Data in a view, you must be able to edit a view in Tableau Desktop, Tableau Online, or Tableau Server.
Build a visualization. Make sure it uses a measure that is aggregated with SUM, AVG, COUNT, COUNTD, or AGG.
In Tableau Online or Tableau Server, you will need to open a view for editing (click Edit in the toolbar).
Select a mark of interest, and then click the Explain Data icon in the tooltip for the mark. In Tableau Desktop, you can optionally right-click the mark and select Explain Data in the context menu.
Note: You must select a single mark. Multiple mark selections are not supported. If Explain Data cannot analyze the type of mark selected, the Explain Data icon and context menu command will not be available. For more information, see Situations where Explain Data is not available.
Read the explanations. Explanations are generated for each measure in the current view that can be analyzed.
If multiple explanations are available, click each explanation tab to see the related details.
If multiple measures are available, click each measure tab for more explanations.
Click the Open icon in the top right corner of an explanation viz to open the visualization as a new worksheet and explore the data further.
This image is an example of the explanations window for Explain Data, with multiple explanations available.
A - Selected Mark. Displays the dimension values of the selected mark to indicate the mark that is being described and analyzed.
B - Measure in Use. Click to select the measure in use for explanations. Explanations are given for one measure at a time. If multiple measures are available, they are displayed as separate tabs here.
C - Expected Value Summary. Describes whether or not the value is unexpected given the other marks in the visualization. Hover over the text in this statement to see details about the expected value range.
If an expected value summary says the mark is lower than expected or higher than expected, it means the aggregated mark value is outside the range of values that a statistical model is predicting for the mark. If an expected value summary says the mark is lower or higher than expected, but within the natural range of variation, it means the aggregated mark value is within the range of predicted mark values, but is lower or higher in that range of values. For related information, see How explanations are evaluated, analyzed, and scored.
D - Explanations List. Displays a list of the possible explanations for the value in the selected mark that Tableau was able to identify. Click an explanation in the list to see a description in the explanation pane on the right.
E - Explanation Description. Displays the selected explanation with a combination of text and vizzes. Click the icon in the top right corner of the viz thumbnail image to open it as a new sheet in the workbook.
Note: Sometimes a mark can be analyzed with no resulting explanations. This is indicated by No Explanation Found in Data. For information on data characteristics that work well with Explain Data, see Requirements and Considerations for Using Explain Data and How Explain Data Works.
F - Status Bar. Displays information about the number of fields considered in the analysis. Click the information tooltip to see the types of fields that have been excluded.
When a data source contains more than 1000 unvisualized measures or dimensions, you might see an alert asking if you want Explain Data to consider more fields. Click Explain All to run an analysis that includes more fields. For more information, see Explain Data: Status Information.
When a data source contains dimensions with a large number of unique values (up to 500), those fields will not be considered for analysis initially. You can select which fields are included for consideration by clicking the Choose fields forYourDataSourceName link in the status bar, or by clicking the Data menu, and then selecting YourDataSourceName > Choose Fields for Explain Data.
Note: Dimensions with more than 500 unique values will not be considered for analysis.