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

AW: st: question on dealing with sample selectivity in panel data


From   <[email protected]>
To   <[email protected]>
Subject   AW: st: question on dealing with sample selectivity in panel data
Date   Mon, 27 Jun 2005 15:55:59 +0200

Hi Shige,

Thanks for the suggestion. Yes, gllamm can, in principle, estimate these models, but there is unfortunately very little documentation on how (save for a slide from a Stata user's meeting). Moreover, I found that it takes a really long time to run the model - over 24 hours in my case (with 32000 obs).

Just to clarify, what I'd like to do is estimate a probit model using something like xtprobit, extract the Mills ratio, and then include that as an explanatory variable in a second stage regression (for observed outcomes) using something like xtreg, re. One problem is that, according to Wooldridge (2002 p.583), the standard errors in the second stage need to be corrected for heteroskedasticity and serial correlation. That's basically the step where I am having some difficulty, and was wondering if anybody had written code that implements the formulas suggested by Wooldrige.

Regards,

Colin

-----Urspr�ngliche Nachricht-----
Von: [email protected] [mailto:[email protected]] Im Auftrag von Shige Song
Gesendet: Monday, June 27, 2005 3:36 PM
An: [email protected]
Betreff: Re: st: question on dealing with sample selectivity in panel data

I remember GLLAMM can do this. You can take a look at www.gllamm.org, you can probably find some materials there.

Shige

On 6/27/05, jyotsna puri <[email protected]> wrote:
> Colin,
> I posted the same question a while ago  too, to no avail.
> Let me know if you hear anything.
> -Jo
> 
> 
> 
> Jyotsna (Jo) Puri
> [email protected]
> 
> 
> 
> 
> ----Original Message Follows----
> From: <[email protected]>
> Reply-To: [email protected]
> To: <[email protected]>
> Subject: st: question on dealing with sample selectivity in panel data
> Date: Mon, 27 Jun 2005 14:16:00 +0200
> 
> Hello,
> 
> A while ago the following question was submitted to the Stata 
> Listserver, but I wasn't able to find a response. As I have the same 
> question, I am resubmitting the question in the hopes that somebody 
> could provide some insights:
> 
>  >While Stata has -heckman- to perform selection corrections for  
> >cross-sectional data, I am wondering whether there are any Stata  
> >commands or user-written programs that allows me to perform selection  
> >corrections for panel data models.
>  >
>  >Specifically, are there any commands or programs based on Jeffrey M.
>  >Wooldridge's paper entitled "Selection corrections for panel data  
> >models under conditional mean independence assumptions" (J. of  
> >Econometrics, 1995)?
> 
> Many thanks,
> Colin
> 
> *
> *   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/
>

*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index