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. Higher than expected / Lower than expected For each explanation, Tableau compares the expected value with the actual value. Possible explanations are evaluated on their explanatory power using statistical modeling. Tableau determines the expected range each time it runs a statistical analysis on a selected mark. The expected range is the range of values between the 15th and 85th percentile that the statistical model predicts for the analyzed mark. The expected value for a mark is the median value in the expected range of values in the underlying data in your viz. The model determines the range of predicted mark values, which is within one standard deviation of the predicted value. Next, data that is in the data source (but not in the current view) is considered and added to the model. The analysis also considers possibly related data points from the data source that aren't represented in the current view.Įxplain Data first predicts the value of a mark using only the data that is present in the visualization. How explanations are analyzed and evaluatedĮxplain Data runs a statistical analysis on a dashboard or sheet to find marks that are outliers, or specifically on a mark you select. For a longer, more in-depth description of these concepts, see the article Causal inference in economics and marketing (Link opens in a new window) by Hal Varian. If you know that B was chosen by flipping a coin, any consistent pattern of difference in A (that isn't just random noise) must be caused by B. A common type of outside knowledge would be a situation where the data was gathered in an experiment. However, you might have outside knowledge that is not in the data that helps you to identify what's going on. A third factor could be causing them both to change, or it may be a coincidence and there might not be any causal relationship at all. Just because two variables seem to change together doesn't necessarily mean that one causes the other to change. The data patterns are exactly the same in each of those cases and an algorithm can't tell the difference between each case. You can't tell just from seeing that relationship in the data that A is causing B, or B is causing A, or if something more complicated is actually going on. Explanations are based on models of the data, but are not causal explanations.Ī correlation means that a relationship exists between some data variables, say A and B. While Explain Data can be used with smaller data sets, it requires data that is sufficiently wide and contains enough marks (granularity) to be able to create a model.ĭon't assume causality. For more information about aggregation, see Data Aggregation in Tableau.Ĭonsider the shape, size, and cardinality of your data. Explain Data can't be run on disaggregated marks (row-level data) at the most granular level of detail. This means that your data must be granular, but the marks that you select for Explain Data must be aggregated or summarized at a higher level of detail. This feature is designed explicitly for the analysis of aggregated data. Use granular data that can be aggregated. When running Explain Data on marks, keep the following points in mind:
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |