Fixed variables in stepwise selection

[larameix]

Hello everybody,

i want to perform regression  analyses and used stepwise selection for selecting confounders. The problem is, that the independent variable i am interested in is not in the model in some cases. Therefore, i want to know if there is a way to somehow fix some of the independent variables so that they are always entering the model and only confounders are selected?

Thanks in advance for your help!

[PaigeMiller · Accepted solution]

I have grave reservations about using any stepwise procedure. Just Google "Problems with stepwise regression" and you'll have enough reading material for a few weeks.

Nevertheless, in PROC REG the INCLUDE option of the model statement forces specific variables to be used.

[larameix]

Thank you very much for your help!