RE: st: RE: Panel data Heckman and FE Tobit

["jyotsna puri" <pjyotsna@hotmail.com>]

Amrita and Alejandro,

Both of you are correct. I guess there should be a way to do Heckman
for Panel data and I had laid out a possible method, a while ago, but I have
not written such a program. I think I will need it so if you are keen,
I could exchange notes with you, once I am along some way.

These are the steps I had thought of:
1. Estimate the selection equation via xtprobit.
2. Get estimates of the Mills ratio.
3. Use the Mills Ratio as an explanatory variable in the response equation
where only the truncated dependent variable is considered, i.e. estimate
this equation for selection =1. This is estimated via xtreg, re with the 
Hausman
test to check for specification.
4. One would have to account for inter-equation correlation and bootstrap
the standard errors accordingly.


-Jyotsna



Jyotsna (Jo) Puri
pjyotsna@hotmail.com
Doctoral Candidate, Department of Agriculture and Resource Economics,
University of Maryland, College Park, MD
I ran the Marine Corp Marathon to help educate.




----Original Message Follows----
From: "Alejandro Lopez-Feldman" <alopezfeldman@ucdavis.edu>
Reply-To: statalist@hsphsun2.harvard.edu
To: statalist@hsphsun2.harvard.edu
Subject: st: RE: Panel data Heckman and FE Tobit
Date: Mon, 4 Apr 2005 09:47:18 -0700 (PDT)

Amrita,

I have asked the same question before and from what I have learned I can 
tell you that there is no command in Stata that can do Heckman with panel 
(except of course the pooled case). Cluster is not equivalent to fixed 
effects or random effects. And there are no user written commands either

I think you are right about tobit.

Alejandro

> ----- Original Message -----
> From: "Amrita Bhattacharyya" <bhattaam@bc.edu>
> To: <statalist@hsphsun2.harvard.edu>
> Sent: Monday, April 04, 2005 9:22 AM
> Subject: st: Panel data Heckman and FE Tobit
>
>
> > Dear Statalisters,
> >
> > I will really appreciate if you could help me with the following:
> >
> > 1) Is there a STATA command to do Heckman model with Panel data? Is
> heckman,cluster proper to use in this case? If Heckman can be done with
> Panel data, is there a way to do iv?
> >
> > 2) Am I right to say that doing fixed effect in Tobit with Panel data
> is
> quite complicated (the only oprtion is programme written by Bo Honore)
> and
> there is no command to do tobit with iv and fixed effect?
> >
> > Thank you for your help in advance.
> >
> > Sincerely,
> > Amrita
> >
> > Fourth Year Doctoral Student
> > Department of Economics
> > Boston College
> > 21 Campanella Way--Room 462A
> > Chestnut Hill, MA 02467
> >
> > tel: +1-617-552-6742
> > fax: +1-617-552-2308
> > *
> > *   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/
>
>

-----------------------------------------
Alejandro Lopez-Feldman
Ph.D. Candidate
Agricultural and Resource Economics
University of California-Davis
*
*   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/