Skip to content

Question about linear mixed model

1 message · Douglas Bates

#
I recommend sending questions like this to the
R-SIG-Mixed-Models at R-project.org mailing list which I have cc:'d on this
reply.  Many of those who read that list can reply faster than I am able to.

On Thu, Sep 11, 2014 at 9:06 AM, Hung-Chih Ku <
Hung-Chih.Ku at utsouthwestern.edu> wrote:

            
When n=1000 and p=500 you are trying to estimate 500,000 random effects
coefficients from 1000 observations which seems a bit optimistic  You may
want to reexamine your model specification.  It doesn't make sense to me.