Hello list,
I have one questions when I run the fixed effects models observations
that are dropped.
> xtlogit hicut2 $x $con, i(zipcode) fe
> note: multiple positive outcomes within groups encountered.
> note: 803 groups (1469 obs) dropped because of all positive or
> all negative outcomes.
Is it appropriate to do the Hausman test when this happens since there
are less observation and the random effects model uses the entire
sample?
Thanks,
Melissa
*
* 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/
