[Limdep Nlogit List] bivariate probit with sample selection for panel data?

[William Greene]

Dear Ms. Rousseau: Your model command (and your letter) does not specify what
kind of panel data model you have in mind.  LIMDEP does not have a built
in fixed effects form of this model.  What you can do to produce a random
effects specification is specify it as a random parameters model.  You
will find some different forms of bivariate probit models for panel data
starting on page E21-31 of the Version 9.0 manual.
Regards,
Bill Greene


----- Original Message -----
From: "Sandra Rousseau" <Sandra.Rousseau at econ.kuleuven.be>
To: limdep at limdep.itls.usyd.edu.au
Sent: Tuesday, February 26, 2008 4:13:34 AM (GMT-0500) America/New_York
Subject: [Limdep Nlogit List] bivariate probit with sample selection for panel data?

Hi,

Is there anyone who can tell me whether it is possible to estimate a
bivariate probit model with sample selection for panel data? And if it
is possible, how should I do it?

I have tried the following command:

BIVARIATEPROBIT;Lhs=INSPKW,VOLD4;Rh1=INSPKW1;Rh2=INSPKW1,LOON;Selection;
Pds=39$

But the estimation does not seem to take the panel structure of the data
into account.

Thanks, Sandra

Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm

_______________________________________________
Limdep site list
Limdep at limdep.itls.usyd.edu.au
http://limdep.itls.usyd.edu.au


-- 
Professor William Greene
Department of Economics
Stern School of Business
New York University
44 West 4th St., Rm. 7-78
New York, NY   10012
http://www.stern.nyu.edu/~wgreene
212.998.0876