3

I know that I can perform a stepwise selection on ordinary linear regression model based on the t-value.

but what about Negative Binomial regression model - or GLM in general? Does it theoretically make sense to perform a stepwise selection on variables bases on P-value resulting from "z-scores" when I am trying to improve Negative Binomial regression model? Is such method recommended?

thank you

Jin-Dominique
  • 831
  • 2
  • 9
  • 18
  • 8
    Stepwise selection is not recommended for any model, including ordinary linear regression. If this doesn't make sense to you / you want to understand why, you may want to read my answer here: [algorithms-for-automatic-model-selection](http://stats.stackexchange.com/questions/20836//20856#20856). – gung - Reinstate Monica Nov 22 '13 at 18:19

1 Answers1

4

(1) Most stepwise selection procedures use the p-value from a z or t-score
(2) Most variable selection methods - including stepwise - have been extended to glm including negative binomial models. So yes, you can use stepwise variable selection.
(3) Almost all statisticians express concern about stepwise variable selection, but in many fields (the biomedical field most notably) this is nonetheless the standard. It's worth having a good feel for standard practices in your field.

charles
  • 2,436
  • 11
  • 13