st: Re: xtreg and suest

[Kit Baum <baum@bc.edu>]

I was going to suggest the fully-interacted-dummy approach, but Dan  
beat me to it.

If you want to allow for heteroskedasticity in this context, why not  
use xtgls?

Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.html


On Apr 9, 2006, at 2:33 AM, statalist-digest wrote:


> Thanks a lot for your suggestion. Your method seems to work well  
> for the
> coefficients of the variables but not for the intercepts which is  
> what I
> am really interested in. Because I am quite sure that the variance of
> the two groups is not equal and since the Hausman test is indefinite I
> would like to estimate two different models and compare the intercepts
> of the two models. Is there a way to do that? Furthermore, is it
> possible to generalize your approach for more than two groups of
> individuals?
*
*   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/