I want to compute an intraclass correlation in a multilevel regression model with a binary dependent variable (i.e., using logit). When a continuous DV is used, the ICC is the proportion of variance in the DV that is accounted for by the clustering (person-level) factor. Is the computation of the ICC the same when a binary DV is used?

I saw another post that dealt with this issue for count data as a DV (i.e., poisson): https://stats.stackexchange.com/a/173857/152743. I am not sure if this formula generalizes when a binary DV is used. As in this example, I am using the glmer function in R.


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.