mixed model with non-continuous numeric response

Daniel Ezra Johnson <danielezrajohnson at ...> writes:

I have survey results where the response is 1, 2, 3, or 4. These can
be thought of as equally-spaced points on a scale, I don't have a
problem with that. (They're actually more like "not at all", "some",
"mostly", "totally"; the subject is judging a stimulus.)

As a bayesian alternative, you could try DPolmm in DPackage which can be 
use with ordinal data and syntax similar to lme(r)

fit1<-DPolmm(fixed=imps79o~sweek+tx+sweek*tx,random=~1|id,prior=prior,
mcmc=mcmc,state=state,status=TRUE)
fit1

Dieter