Re: [R] bVar slot of lmer objects and standard errors

From: Ulrich Keller <uhkeller_at_web.de>
Date: Tue 21 Feb 2006 - 11:04:02 EST

Hello,

I'm sorry to resurrect this thread that I started almost two months ago. I've been pretty busy since I posted my question and the issue is not that high on my priority list. Thanks to all those who replied, and I hope I can tickle your interest again.

As a reminder, my question was how one can extract the conditional posterior variance of a random effect from the bVar slot of an lmer model. Thanks to your answers, I now understand that I have to use the diagonal elements of the conditional matrices. However, I am not quite sure what this means:

Douglas Bates wrote:
> I'd have to go back and check but I think that these are the upper
> triangles of the symmetric matrix (as Spencer suggested) that are the
> conditional variance-covariance matrices of the two-dimensional
> random effects for each school up to a scale factor. That is, I think
> each face needs to be multiplied by s^2 to get the actual
> variance-covariance matrix.

What is s^2? Where can I find it in the lmer object? I tried reading the source, but gave up fairly quickly. Thanks in advance for your replies, and this time I promise I'll be more responsive.

Uli

My original post:
> Hello,
>
> I am looking for a way to obtain standard errors for emprirical Bayes estimates of a model fitted with lmer (like the ones plotted on page 14 of the document available at
http://www.eric.ed.gov/ERICDocs/data/ericdocs2/content_storage_01/0000000b/80/2b/b3/94.pdf). Harold Doran mentioned (http://tolstoy.newcastle.edu.au/~rking/R/help/05/08/10638.html) that the posterior modes' variances can be found in the bVar slot of lmer objects. However, when I fit e.g. this model:
>
> lmertest1<-lmer(mathtot~1+(m_escs_c|schoolid),hlmframe)
>
> then lmertest1@bVar$schoolid is a three-dimensional array with dimensions (2,2,28). The factor schoolid has 28 levels, and there are random effects for the intercept and m_escs_c, but what does the third dimension correspond to? In other words, what are the contents of bVar, and how can I use them to get standard errors?
>
> Thanks in advance for your answers and Merry Christmas,
>
> Uli Keller



R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Tue Feb 21 11:09:10 2006

This archive was generated by hypermail 2.1.8 : Fri 03 Mar 2006 - 03:42:38 EST