> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Paul Chin
> Sent: Tuesday, January 11, 2005 2:53 PM
> To: [email protected]
> Subject: st: Bivariate Probit Model
>
>
> Dear users,
>
> I am a new STATA user and trying to build a bivariate model using
> biprobit.
> If I would like to do 10-iteration model building processes,
> for each iteration I only randomly sample 70% of my development sample
> file
> and would like to keep models' coefficients.
> What is the best way to do it? What commands should I use?
> Thank you for any help.
Paul,
Here is one way, which will save the coefficients as a separate data file.
use http://www.stata-press.com/data/r8/school.dta, clear
forv i = 1/10 {
tempfile tf`i'
preserve
sample 70
qui parmby "biprobit priv vote logptax loginc year", ///
saving(`"tf`i'"', replace)
local files "`files' `"tf`i'"'"
restore
}
dsconcat `files', dsid(id)
This requires Roger Newson's -parmby- and -dsconcat-. You can use -findit
parmest- to locate and download the files from Stata Journal 3(3) and 4(3)
Hope this helps,
Scott
*
* 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/
