st: HT estimator without endogenous time invariant vars

[Seema Bhatia <ler02sb@reading.ac.uk>]

Hello all

I am working with the HT estimator to estimate my model as a FE model is not 
appropriate for my study but the Hausman test suggests correlation between 
the X's and the individual effects. I know that the theory says that the 
rule is that k1 > g2 for overidentification. But what if is suspect that 
none of the time invariant variables in my model are endogenous? Is it still 
ok to use the HT estimator?

I would be very grateful for any guidance on the matter.

Many thanks

Seema

Seema Bhatia-Panthaki
Research Postgraduate
University of Reading
UK


*
*   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/