Stepwise Regression Options in GRM

These options are available only when either the Forward stepwise (effects can be entered or removed), Backward stepwise (effects can be removed or entered), Forward entry (effects can only be entered, and never be removed), or Backward removal (effects can only be removed, and once removed, never be re-entered into the model) option button is selected on the Quick Specs Dialog - Options tab or the GRM Analysis Wizard Extended Options - Advanced tab. The options described here are used to steer the stepwise selection procedure; for a description of stepwise model building procedures, refer to Model building in GRM in the Introductory Overview.

Element Name Description
p1, enter, p2, remove If p1, enter option button is selected, the stepwise entry or removal of effects into or out of the model is guided by the significance levels (p-values) specified in the p1,enter and p2, remove fields. In other words, an effect will be entered into the model if the statistical significance of its contribution to the prediction is better than (i.e., p less than) p1, enter; an effect will be removed from the model if the statistical significance of its contribution is worse than (i.e., p greater than) p2, remove. Thus, in Forward stepwise and Backward stepwise selection, where at each step effects can be entered into or removed from the model, p1, enter must be less than p2, remove, so that effects that are entered are not automatically removed in the next step, or vice versa. The p2, remove value is ignored when Forward only is selected; the p1, enter value is ignored when Backward only is selected.
F1, enter, F2, remove If the F1, enter option button is selected, the stepwise entry or removal of continuous predictor variables into or out of the model is guided by the F values specified in the F1, enter and F2, remove fields. In other words, a predictor will be entered into the model if the F value associated with the statistical significance of its contribution to the prediction is greater than F1, enter; a predictor will be removed from the model if the F value associated with the statistical significance of its contribution is worse than F2, remove. Thus, in Forward stepwise and Backward stepwise selection, where at each step effects can be entered into or removed from the model, F1, enter must be greater than F2, remove, so that effects that are entered are not automatically removed in the next step, or vice versa. The F2, remove value is ignored when Forward only is selected; the F1, enter value is ignored when Backward only is selected. These options are only available if only continuous predictors are in the model (i.e., no categorical predictors); this is because F values for effects with different degrees of freedom (greater than 1) are not comparable, and hence, meaningful selections of effects can not be based on their comparison.
Note: when you run a stepwise regression with multiple dependent variables, the F/p, enter/remove are taken from the respective F/p values for the multivariate Wilks' Lambda test.
Max. steps Specify the maximum number of steps that is to be performed in the stepwise selection of effects in the Max. steps field.

See also GRM - Index.