Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: -by varname- and -est store-


From   Alan Marshall <Alan.Marshall@postgrad.manchester.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: -by varname- and -est store-
Date   Wed, 16 Aug 2006 16:57:31 +0100

Dear Bernhard,

Coincidentally I was about to email the stata list with almost exactly the same
question! I'm using the by command with nl (non linear regression) and I also
want to store my parameter estimates but can only retieve the estimates
assocaited with the last by variable.

I'd really appreciate it if you could forward any advice you recieve on to me.

Thanks

Alan

Quoting Bernhard Ganglmair <bganglma@uni-bonn.de>:


Hi,

I am struggling with -by- and the -estimates- command. Hopefully somebody can give me a hint.

I estimate a bivariate probit model for each value of the variable varname using clustered data, i.e. for various sub-populations defined by varname. The first approach that came into my mind was just running the biprobit with if varname==some value. The Stata manual on survey, however, tells me that I would incorrect variance estimates if I used -if-. It is suggested to use the by() or subpop() option. Since byprobit doesn't allow for by() or subpop() [version 8; no svybiprobit], I am running the following:

by varname, sort: biprobit y1 y2 varlist, cluster(ea)

For each value of varname I'd like to store the estimation results, -est store- however gives me only the results of the last value in varname.

How do I address results generated using -by-?

Best, Bernhard

*
* 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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index