Is it possible/recommended to compare the -2*Log-Likelihood (-2LL) value of a Generalized Linear Mixed Model (GLMM) against the -2LL value (and/or AIC/AICC/BIC) of a Linear Mixed Model (LMM) with the same predictor/outcome variables? The GLMM uses NORMAL distribution with IDENTITY link function, with ROBUST estimation. Coefficients and p-values are usually quite close for the same variables, but sometimes they are different. Is it possible to make a comparison between the two models using -2LL?
