Re: [R] best subset selection on random effects model

I don't know of any package that will do it (or if violating the marginality principle by having non-nested models even makes sense) but you could always build your own search through all possible models. Problem is for a large number of fixed effects this can take a good bit of time... Here is a

Re: [R] best subset selection on random effects model

The question is where do your models come from? Passing nested models to ?anova.lme in nlme package or lme4 results in a likelihood ratio test. Are you looking for something else/more ? On Sun, Feb 12, 2012 at 8:02 PM, Tao Zhang zt020...@gmail.com wrote: Hi,     I know leaps() computes the

[R] best subset selection on random effects model

Hi, I know leaps() computes the best subset selection for linear model, and the bestglm() computes the best subset selection for generalized linear model. Is there any package for best subset selection on random effects model, or mixed effects model? Thank you so much. Tao