Statalist The Stata Listserver


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

st: ordered probit and sample selection


From   Jenny Säve-Söderbergh <Jenny.Save-Soderbergh@sofi.su.se>
To   statalist@hsphsun2.harvard.edu
Subject   st: ordered probit and sample selection
Date   Sun, 22 Oct 2006 21:09:52 +0200 (CEST)

Dear all, 

I want to estimate an ordered probit model conditional on a selection equation. 
I have two problems.  

My first method has been to try the ?ssm? command. But even after 36 hours 
there I have received no results. Is this reasonable given that I have 18000 
individuals, 10 variables in the first equation and 8 variables in the second??

Second, I want to change strategy to use an ordered probit with a Mills ratio, 
included from a bivariate probit for the selection equation. I did read the 
reply by Maarten Buis on the 5th of October "Inverse mills ratio and ordered 
logit " and hence prefer to use this method. But what does this procedure imply 
for the error terms and can it create a bias? Does the error terms have to be 
corrected and, if so, how?

I am very grateful for any help, 

Jenny 

*
*   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