Susan,
Your weights at levels 1,2,etc. should
all have the same variable name except for
the last character which should be 1,2,etc..
For example, the weights could be in variables
pw1, pw2, and pw3. You would then use the
pweight(pw) option.
It is important to omit the last character of the
variable names in the pweight() option.
If you specify pweight(pw1), gllamm will look for
pw11, pw12, and pw13.
I hope this helps.
Sophia
----- Original Message -----
From: "Paddock, Susan" <[email protected]>
To: <[email protected]>
Sent: Thursday, October 02, 2003 3:04 AM
Subject: st: gllamm "probability weight variables not found"
> I am running gllamm (latest version) and want to use the "pweight"
> statement. When I enter either of the following commands that are below
> (specifying either 1 weight or 2 weight variables), I receive the
following
> error message: "probability weight variables not found." I know that the
> weight variables are in the data set, because they appear when I type
> "describe" and the model runs when I put them in as predictors (just as a
> check). The program runs when I exclude the pweight statement. Any
> thoughts/advice would be appreciated.
>
> The statements are:
>
> gllamm y anydrug anydx black hispanic othrace chronic employed, i(site)
> pweight(level2w) family(bin) link(logit)
>
> gllamm y anydrug anydx black hispanic othrace chronic employed, i(site)
> pweight(wigivenj level2w) family(bin) link(logit)
>
> Thanks,
> Susan
> *
> * 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/
*
* 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/
