Statalist


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

st: Hausman Taylor Test to check for REv/s FE


From   Seema Bhatia <ler02sb@reading.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   st: Hausman Taylor Test to check for REv/s FE
Date   Wed, 28 Nov 2007 15:16:14 -0000

Hello there

I have a question about the HT test for the use of of FEv/sRE

What would happen if while testing for the more efficient estimator, I 
specified Re as robust? Therefore instead of

xtreg depvar indepvar 1........................indepvarn, re

I specify

xtreg depvar indepvar 1........................indepvarn, re robust?

I did this just as a test out of curiosity (without considering the full 
implications of this) and I find that the differenc in the two commands 
changes the  Prob>chi2 dramnatically so that in the former case FE is 
appropriate and in the latter RE is appropriate

Any guidance on this would be useful.

Many thanks

Seema


*
*   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