My initial hunch is no, since in case control data (assuming $y_i$ is a binary response, i.e. = 1 for case, 0 for control), we match a control (or several) per case. Meaning the data is very much dependent given the strata. But I saw this question here which made me think I might be wrong.

So, can GLMM be used with Case-Control data?


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.