RE: re:RE: st: unconditional fixed effect logit

["Noh, Grimm" <grimmnoh@wharton.upenn.edu>]

I see.

But then the problem is that I'll be controlling for the unobserved heterogeneity of each 'firm-country pair', 
not the unobserved heterogeneity of each 'firm'.

Is there a way to control only for the heterogeneity of each 'firm' when my data structure is by firm-country-year?

Thank you so much.


Grimm


________________________________________
From: owner-statalist@hsphsun2.harvard.edu [owner-statalist@hsphsun2.harvard.edu] on behalf of Christopher Baum [kit.baum@bc.edu]
Sent: Sunday, January 30, 2011 1:07 PM
To: statalist@hsphsun2.harvard.edu
Subject: re:RE: st: unconditional fixed effect logit

<>
> Sorry, but I didn't quiet understand.
> I want to know how I can run unconditional fixed effect logit, controlling for unobserved firm effects,
> when my data structure is firm-country-year, not firm-year.
>
> I didn't quiet get how egen helps me do that.


If you have firm-country-year data, and want to convert it into (firm+country)-year data, you need a variable identifying each distinct combination of firm and country so that you can xtset the data by (i) and (t). To create such a variable, which then becomes the (i), use egen combo = group(firm country) and then you may use combo in xtset.

Kit

Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                              An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
   An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html


*
*   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/
*
*   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/