Statalist


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

Re: st: xtlogit vs. logit with dummies


From   "David W. Harless" <dwharles@vcu.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: xtlogit vs. logit with dummies
Date   Thu, 02 Aug 2007 09:09:19 -0400

Sarit,
Unlike the cases of OLS and Poisson regression, fixed effects logit is not equivalent to logit with dummy variables for the cross-sectional units. Logit with dummy variables for the cross-sectional units produces inconsistent estimates except in the unusual case where the number of observations per group is large. There is a short entry on this in the Stata manual description for -clogit- under the section "Fixed-effects logit" (p. 224 of Version 9 Reference A-J manual) which gives some references.
Dave Harless

Sarit Weisburd wrote:

Hello,

I am confused by the large estimated differences I see when using
xtlogit fe by(hid)
and logit with dummies for hid. Does anyone know why the results are
so different? Which one is more correct?


Thanks,
Sarit
*
*   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/
*
*   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