On Jun 4, 2004, at 7:33 AM, Andrea wrote:
Thanks for that. However, adding 420 dummies to my model would only
work
when estimating a pooled OLS, but not a within estimator (since the
fixed
effects model would drop anything that is invariant over time).
Any hints for doing that in fixed effects?
A one-way individual fixed effects model drops any variable that is
constant for an individual, such as gender or race. As in previous
post, it makes no difference algrebraically whether you estimate this
model with the within transformation or by explicit dummy variables.
The rank of X'X will be the same any way you do it. You cannot include
time-invariant variables in an individual FE model.
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/
