Statalist The Stata Listserver


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

st: Biprobit for panel data


From   Magdalena Norberg-Schönfeldt <Magdalena.Norberg-Schonfeldt@econ.umu.se>
To   statalist@hsphsun2.harvard.edu
Subject   st: Biprobit for panel data
Date   Thu, 16 Nov 2006 20:11:26 +0100

Hi,
I am quite new to Stata and have alredy run in to problems =) (trust me, I am not blaming Stata for that...). I have a pair of probits where the dependent variable of the second equation is included as an explanatory variable in the first equation, as I understand it, this is not a problem in the biprobit command. I have successfully (I hope) alredy estimated the model for cross sections whit the robust cluser command and found a significant correlation between the two equations, but, my problem is that the data is an unbalanced panel and I would like to extend the model to account for random effects in order to actually use the panel structure, and I do suspect that there are individual specific effects. Is it possible to run biprobit together with an xt command?

And, does anybody have an idea about how the results can be expected to change when using an xt command compared to just using robust cluster?

Thanks for your time!
/Magdalena


----------
MAGDALENA NORBERG-SCHÖNFELDT
DEPARTMENT OF ECONOMICS • UMEÅ UNIVERSITY • SE-90187 UMEÅ • SWEDEN
TELEPHONE: + 46 90 786 61 46 • FAX: + 46 90 77 23 02
EMAIL: magdalena.n-schonfeldt@econ.umu.se



*
* 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