Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: sureg, a panel data estimator


From   baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: sureg, a panel data estimator
Date   Wed, 23 Oct 2002 10:15:44 -0400

--On Wednesday, October 23, 2002 2:33 -0400 Jeremy wrote:

Nik's question as well as my original one, however, is legitimate. You may
think that "sureg" is a panel data estimator, but it does not handle fixed
effects by itself. Your example clearly indicated that you had to combine
"sureg" with "xtreg" to deal with the issue at hand, which was exactly
what I didn't but wanted to know about when I raised my question.
Therefore, your claim that by using "sureg," one is already estimating
fixed effects is, I hate to say, less than true.
I did not combine xtreg,fe with sureg; I ran them as alternative estimators of a model involving the Grunfeld data. sureg is indeed estimating fixed effects, if one takes fixed effects in the vernacular to mean a unit-specific intercept. Each sureg equation has an intercept, with an i subscript. How is that not a fixed effect?

As I stated at length yesterday, the SUR model also allows slopes and the s^2 to vary, which a standard fixed-effects model on 'long' format data does not (although one could dummify the slopes to achieve that end). But in my mind the (unobserved) intercept of a fixed-effects model with subscript i and the constant term of the equivalent sureg equation i are estimates of the same underlying population parameter: the conditional mean of y for unit i, with all regressors equal to zero.

Kit
*
* 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