QTRSELECT Procedure
SELECTION Statement
SELECTION <METHOD=method <(method-options)>><options>;
The SELECTION statement performs model selection by examining whether effects should be added to or removed from the model according to rules that are defined by model selection methods. The statement is fully documented in the section SELECTION Statement in Chapter 2, Shared Concepts.
The QTRSELECT procedure supports the following values of the METHOD= option in the SELECTION statement:
- BACKWARD
specifies the backward elimination method, which starts with all effects in the model and deletes effects.
- FORWARD
specifies the forward selection method, which starts with no effects in the model and adds effects.
- NONE
specifies no model selection.
- STEPWISE
specifies the stepwise regression method, which is similar to the forward selection method except that effects already in the model do not necessarily stay there.
By default, METHOD=STEPWISE.
The DETAILS=ALL and DETAILS=STEPS options produce the "Fit Statistics," and "Parameter Estimates" tables, which provide information about the model that is selected at each step of the selection process.
By default, the QTRSELECT procedure displays the stop horizon steps in the "Selection Summary" table, and uses these steps for choosing the final model of the model selection process. Therefore, it is possible that the final model occurs after the step that has the best stop criterion value. To exclude the stop horizon steps for choosing the final model, you can specify the following option:
If you specify the PLOTS=CRITERIA or PLOTS=ALL option, then a plot of the fit criteria by the selection step is created for the AIC, AICC, SBC, R1, and adjusted R1 statistics. If you also specify a PARTITION statement, then the same type of plot is created for the ACL criteria for training, validation, and testing roles. If you specify the PLOTS=FITBYROLE option and a PARTITION statement, then a plot of the ACL criterion by the selection step for each role is created.