p values in stepwise discriminant analysis

cormac

I'm new to multivariate analysis so this should be an easy one: When doing stepwise analysis for discriminant analysis between two groups, why are there one set of p>F values for when all the features are ticked and a totally different set for when they are all ticked?

michael_jmp

Hello cormac,

Are you referring to the different sets of Prob>F values at various stages of the stepwise analysis?

You can read about the Stepwise Variable Selection option in Discriminant here: Discriminating Groups.

The following information will be in the documentation for JMP12, and I think it will help you understand where the F Ratios and p-values are coming from.

When you enter or remove variables from the model, the F Ratio and Prob>F values are updated based on an analysis of covariance model with the following structure:

• The covariate under consideration is the response.

• The covariates already entered into the model are predictors.

• The group variable is a predictor.

The values for F Ratio and Prob>F given in the Stepwise report are the F ratio and p-value for the analysis of covariance test for the group variable. The analysis of covariance test for the group variable is an indicator of its discriminatory power relative to the covariate under consideration.

Regards,

Michael