Re: st: glm and proc mixed

[Buzz Burhans <wsb2@cornell.edu>]

There is no full equivalent in Stata to PROC MIXED.

Limited capability in Stata itself is provided by some, but not all, of the 
xt series of commands: xtreg, xtlogit, xttobit, xtregar, xtrchh, xtprobit, 
xtpoisson, xtnbreg, xtivreg, xtintreg, xthtaylor, xtcloglog, xtabond.  In 
general, these commands often allow for a random intercept, but not random 
covariate effects, and often have little capability to model between or 
within panel error covariance.

Alternatively, a much more flexible user written program is available: 
gllamm.  GLLAMM also has limited capability for applying structured 
covariances.

There is not, at this time, a full equivalent to Proc Mixed.  Stata is 
reportedly working on one; many of us are anxiously awaiting it's release.

Buzz Burhans
Cornell University Dept. of Animal Science



At 04:22 PM 4/22/03 +0200, you wrote:

> Dear all,
>
> I have to study generalized linear regression model with repeated measures.
> I know  that with SAS, the function is PROC MIXED
>
> What is the equivalent with Stata ?
>
> Thanks
>
> Alvine bissery
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/