Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: Fixed Effects Probit Model.


From   antonio martuscelli <totissoit@yahoo.it>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Fixed Effects Probit Model.
Date   Fri, 29 Jul 2011 11:17:34 +0100

One fix to this problem could be the Mundlak (or Chamberlain)
correction. This comes at the cost of making certain assumptions on
the distribution of the random effect. Basically (in the Mundlak
version) you add as additional explanatory variables the within-group
(firm in your case) means of all the covariates and then run the model
as a random effect probit. The introduction of the means should
capture the correlation between the unobserved heterogeneity and the
covariates that renders the random effect model inconsistent. The
procedure is explained very well in Wooldridge's book, in several of
Greene's WP available on his web-site and of course in the original
paper by Mundlak.

Another possibility might be, depending on the type of analysis,
estimating a logit fixed effect which is instead a consistent
estimator and is available as a command in Stata.

Best,

Antonio

On 29 July 2011 09:48, natasha agarwal <agarwana2@googlemail.com> wrote:
>
> Dear All,
>
> I have a firm-level unbalanced panel data set (20,000 firms for 5
> years), and wanted to run a two-way fixed effect probit model.
>
> From the reading I have been doing, it seems that Stata has no command
> (like the xtreg, fe) to run the fixed effect probit model. I could
> introduce a dummy for each firm for controlling for unobserved firm
> heterogeneity. However, if I do so, then I run into the incidental
> parameter problem. Besides, Stata takes allot of time to estimate the
> same.
>
> Is there any other reading, or program, or command, if anybody could
> help me with, so that I can estimate the same?
>
> Looking forward for a valued response.
>
> Many thanks
> Natasha
> *
> *   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/

-- 
Antonio Martuscelli
University of Sussex
Department of Economics

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index