[R] Confidence Intervals for Random Effect BLUP's
Gregor Gorjanc
gregor.gorjanc at bfro.uni-lj.si
Sat Nov 10 10:53:42 CET 2007
Rick Bilonick <rab <at> nauticom.net> writes:
...
> I think prediction interval is what is usually used. Regardless, I'm not
> sure how "predict.lm" will be of much help because I asked specifically
> about BLUP's for random effects and the last time I checked lm did not
> handle mixed effects models. Neither predict.lme and predict.lmer
> provide intervals. Here is the code that I included in my original
> e-mail. My simple question is, will this code correctly compute a
> prediction interval for each subjects random effect? In particular, will
> the code handle the bVar slot correctly? Some postings warned about
> inappropriate access to slots. Here is the code that I asked about in my
> original e-mail:
Rick,
I can not help you with your code as I am not familiar with slots in lmer
outputs. Maybe lmer authors can help you - try on r-sig-mixed list.
But you can check your results with running MCMC for the same model and
you will get the whole posterior density of all your parameters that
you put on prior with unknown variance i.e. "random" effects or sometimes also
called BLUPs. There is a function in lme4 package that can do that!
Gregor
More information about the R-help
mailing list