This command is available with the Predictive Analytics Module. Click here for more information about how to activate the module.
If the analysis uses k-fold cross-validation or no validation, then the statistics in the response information table give the summary statistics for the response data.
If the analysis uses a test data set to evaluate the performance of the model, the descriptive statistics are separate for the two data sets. If the performance of the model on the test data set is different from the performance on the training data set, you can examine the descriptive statistics to look for differences in the two data sets. Systematic differences between the training and the test data set can indicate information that is missing from the analysis.