Re: st: multilevel modeling with svy commands

["Michael N. Mitchell" <Michael.Norman.Mitchell@gmail.com>]

Dear Ming

  I think your question is very similar to

http://www.stata.com/statalist/archive/2010-04/msg01317.html

  in which Steve Samuels noted that the -gllamm- command will accept weights (but not 
strata), but you could consider adding the strata variable as a series of dummies to try 
and account for the variance of the strata variable.

I hope that helps,

Michael N. Mitchell
Data Management Using Stata      - http://www.stata.com/bookstore/dmus.html
A Visual Guide to Stata Graphics - http://www.stata.com/bookstore/vgsg.html
Stata tidbit of the week         - http://www.MichaelNormanMitchell.com



On 2010-08-09 8.43 PM, Ming Wen wrote:
> Hi there,
>
> Has anyone tried to use Stata to conduct weighted multilevel models (random=
>   effects) that take account for the multistage sampling design (with PSU, S=
> trata and Weight)? I know SAS can run this kind of models but don't know ho=
> w to combine xt- commands with svy- commands to achieve this goal.
> Any response would be appreciated.
>
> Best,
>
> Ming
> *
> *   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/