Noori Akhtar-Danesh <[email protected]> wrote:
> I am using gllamm program on a large national survey with weights.
> However, when I use the following command, I get the message that
> "probability weight variables not found" while the weight variable is
> available in the dataset.
> What do I need to do differently?
>
> Here is the command that I use (it works without weights):
>
> gllamm HWTEGBMI Age SEX MS, i( GEOEGPRV) adapt pw(WTSE_S1M)
How many weight variables and levels do you have? I think you should
have one weight variable for each level, and only specify the stub of
the weight variables in the pweight() option. For example, if you have
your level-1 weights in variable wt1 and your level-2 weights in
variable wt2, then you would specify the pweight() option as
pweight(wt).
Anders Alexandersson
[email protected]
*
* 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/
