I conducted a multilevel latent class analysis with a large dataset gathered from five different sites, with site specified as the grouping variable. The best fitting model included 2 classes and only one group (suggesting, I think, that the classes did not vary by site). I then used a three-step procedure to predict a dependent variable from the two identified classes. Is there a need to account for site in the three-step analysis as well or is that covered by the original multilevel latent class analysis?

  • $\begingroup$ You might want to spell out your acronyms once to make sure readers understand what you are asking (LCA and DV). $\endgroup$
    – R Carnell
    Feb 15 at 19:32

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.