Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: Bivariate probit with sample selection


From   "Scott Merryman" <smerryman@kc.rr.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Re: Bivariate probit with sample selection
Date   Thu, 20 Feb 2003 19:14:55 -0600

----- Original Message -----
From: "Bo Wandschneider" <bo@uoguelph.ca>
To: "stata" <statalist@hsphsun2.harvard.edu>
Sent: Thursday, February 20, 2003 10:02 AM
Subject: st: Bivariate probit with sample selection


> We are new to Stata and are still learning our way around this package -
> different philosophy than things like SAS, TSP, Shazam or Limdep.  We
> have a user who wants to duplicate some results they had in Limdep.
>
> In limdep we simply ran the individual probits, stored the betas and
> used these as starting values in the bivariate probit.  After this
> equation we entered the Select command for sample selection.   We can
> get to the bivariate probit (without the starting values), but are
> unsure how to program the next step.   We have checked manuals, but
> don't have the 'SVY' manual (we are ordering it)
>
> Any suggestions were to look ... just need a starting point -
>
How about using -heckprob- for the probit with sample selection and then
using -suest- to combine the equations.  Something like this:

webuse school
heckprob private years logptax, sel(vote = years loginc logptax) score(s1*)
estimates store eq1
heckprob school years logptax, sel(vote = years loginc logptax) score(s2*)
estimates store eq2
suest eq1 eq2

I 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/



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