I had data with repeated measurement and nested design. Conventional ANOVA requires strict control on homogeneity of variance and repeated measurement ANOVA requires assumption of sphericity. Multi-level modeling allows greater flexibility as the covariance matrix could be modified and thus, I used Linear Mixed Model(LMM) option in SPSS and defined the repeated measurement matrix with AR(1).

I am confuse do I still have to keep the assumption of homogeneity of variance if I use LMM.

My dependent variable is a continuous scale data, can I use a Generalized Linear Mixed Model (GLMM) for analysis if homogeneity of variance is not met? However, my data is not binomial distributed.

Thank you.


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.