I have a matched case-control study design, where the outcome is continuous (and highly skewed), and there are multiple confounding variables.

I have found a lot of literature discussing the use of conditional/unconditional logistic regression models, but these are all focused on matched case-control studies with dichotomous outcomes.

What kind of regression model would be appropriate with a continuous outcome? Would the general linear model suffice? What about the case of a highly skewed continuous outcome?

  • $\begingroup$ If your outcome is continuous it does not make sense to talk about logistic regression. A (gaussian) linear model is what you need, probably. Also what do you mean that you have confounding variables? In your data? $\endgroup$ – user2974951 Aug 7 at 8:56

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.