st: Categorical variable models - weight option

[Leonor Saravia <lmisaravia@gmail.com>]

Dear Statalisters,

Currently, I am working with social protection database, with which I
have estimate different models, like OLS and 2SLS. Ussualy, when I run
these kind of models I use the analytic weights ('aweight') to expand
the sample to the population estimates. Now, I am performing
categorical variable models: logit, probit, multinomial logit and
multinomial probit, but when I try to use the 'aweight' option on the
probit or logit estimation, Stata brings this error: "aweight not
allow". However, when I run the mlogit or mprobit (usig Stata 10), the
regression runs well.

I think that the option in this kind of models is to use the 'pweight'
option, but I do not know if this is correct or if it is a better
option not to use weights . I would greatly appreciate your
suggestions and advice on applying the "weight" option.

Kind regards,

Leonor Saravia
*
*   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/