Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: AW: Question_Heckman-Test_Mills-ratio


From   "Martin Weiss" <martin.weiss1@gmx.de>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: AW: Question_Heckman-Test_Mills-ratio
Date   Wed, 6 May 2009 17:54:29 +0200

<> 

I highly recommend you read up on -heckman- in
http://www.stata-press.com/books/mus.html, chapter 16.6, or the manual entry
[R] heckman. 

The whole point of the -twostep- estimator is that you derive the mills
ratio from the first stage -probit- and plug this estimator into the second
stage estimation. You can do that by hand, but you would have a hard time
adjusting the standard errors for the fact that one of the regressors in the
second stage is based on an estimate (with an associated sampling variance)
itself. So it is much easier to have all of it done via -heckman-...


HTH
Martin


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von ??
Gesendet: Mittwoch, 6. Mai 2009 17:44
An: statalist
Betreff: st: Question_Heckman-Test_Mills-ratio

Dear STATA List!

It seemed that Mills ratio is based on the first probit regression instead
the first and second stage of the model. 
Then what is the function of heckman two step here? 
Thank you!

*
*   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/


*
*   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/



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