Scott,
The the general linear mixed model is defined
by
Y=XB+ZU+ e
E(Y)=XB
V=Cov(Y) = ZGZ' + R
where
the G matrix is the covariance matrix for the random effects and the R matrix is that for the repeated effects.
The random effects are specified after the || and the within subjects (repeated effects) are specified by cov( )
in the xtmixed command.
Robert A. Yaffee, Ph.D.
Research Professor
Silver School of Social Work
New York University
Biosketch: http://homepages.nyu.edu/~ray1/Biosketch2008.pdf
CV: http://homepages.nyu.edu/~ray1/vita.pdf
----- Original Message -----
From: Raphael Fraser <[email protected]>
Date: Tuesday, February 10, 2009 1:06 pm
Subject: Re: st: xtmixed: cov structure for within REs
To: [email protected]
> Perhaps if you provide the SAS code we could translate into Stata.
>
> On Mon, Feb 9, 2009 at 2:32 PM, SR Millis <[email protected]> wrote:
> > In xtmixed, is it possible to model the covariance structure for the
> within-individual random errors (R matrix), ie, an xtmixed equivalent
> of the "repeated" statement in SAS?
> >
> > Of course, using "random" and "repeated" statements in SAS likely
> over-specifies the model--and non-convergence often occurs.
> >
> > Thanks,
> > Scott
> >
> >
> >
> > *
> > * For searches and help try:
> > * http://www.stata.com/help.cgi?search
> > * http://www.stata.com/support/statalist/faq
> > * http://www.ats.ucla.edu/stat/stata/
> >
>
>
>
> --
> Raphael A. Fraser, MSc
> Lecturer in Biostatistics
> Tropical Medicine Research Institute
> Faculty of Medical Sciences
> University of the West Indies
> Mona Campus
> Kingston, JAMAICA
>
> Tel: (876) 927-2471; 977-6151
> Mobile: (876) 410-4699
> Fax: (876) 927-2984
> e-mail: [email protected]
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
