[R-sig-ME] fixed effect testing again (but different)

Doran, Harold HDoran at air.org
Thu Aug 28 20:13:14 CEST 2008

> Up until now my procedure is to evaluate two models, viz.
> m0 <- lmer(response~(1|subject),data)
> m1 <- lmer(response~gender+(1|subject),data)
> The likelihood-ratio test approach directly compares these two.

Since these models differ in their fixed effects, you need REML=FALSE
for the LRT to be meaningful.

More information about the R-sig-mixed-models mailing list