Select the results to display for CART^® Regression

Select the tables that you want to display for the analysis.

Method

Display information about model validation, node splitting method, and other information about the analysis.

Response information

Display descriptive statistics about the response variable, such as the mean and standard deviation.

Model summary

Display the statistics that describe the model. Includes the number of predictors, the important predictors, the number of nodes, and goodness-of-fit information about the model.

Percent error statistics due to K% largest residuals; K=

Display the error statistics for both the training and test data for the largest residuals.

You can specify the percentage to display, 0 < K ≤ 100. K=20 is the default value, which means that up to 20% of the largest residuals are displayed.

Terminal node type

Choose whether to display the best nodes, the worst nodes, or both for the Fits and error statistics table and the Criteria for classifying subjects table.

• Best: By default, Minitab displays the best terminal nodes. The best nodes have the lowest MSE or MAD values.
• Worst: Select to display the worst terminal nodes. The worst nodes have the highest MSE or MAD values.
• Best and Worst: Select to display the best and worst terminal nodes.

Response fits and error statistics by K terminal nodes; K=

By default, Minitab displays 5 terminal nodes.

Criteria for classifying subjects into K terminal nodes; K=

By default, Minitab displays 5 terminal nodes.