Logistic regression analysis for two treatment groups and two time points?

[Biochemist]

Thanks for the answer, reason180.

I am bit confused now. Even though I don't want to compare treatment A and B regarding their effectiveness, I still want to find out the individual predictors for a response in case of treatment A or treatment B, and these may not be the same for the two treatments. If I just handle treatment A and B as if they were the same, then I wouldn't be able to do that, right?

[reason180]

That's correct.

[reason180]

Sounds like you need to include A vs B as a factor, *and* you need to examine the interactions of that factor with other predictors.

[Biochemist]

Thanks for the advice. It gets more complicated than I expected.