Hi there,
I'm trying to do the following: estimating xtlogit, fe and re and
compare only the coefficients for one variable. I could run re only and
include the mean and the de-meaned variable and then apply test
mean=de-mean. Unfortunately, the variable under consideration is binary,
hence there is perfect collinearity and stata excludes them. Is there
any easy way to compare coefficients from two estimations? Can the
Hausman test be manipulated to test sub-groups of variables?
Thanks
Axel
*
* 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/
