Dear statalist,
I'm a new user of stata and I work with panel data. I have a doubt, it's very important to me because I don't understand a thing.
When you use for example the command xtgls, you are supposing that there exists correlation or heteroskedasticity in the error term Eit.
But what about the indivual effects Vi? How do you know if they are correlated with the explanatory variables Xit? Because then, you should estimate using a kind of command xtgls, fe?
This question extends to any other commands with panel data, like xtgee,...
How do we separate the problems that the individual effects Vi may generate with the problems that Eit may generate?
I will much appreciate any help about this question.
Thanks a lot!
_________________________________________________________
http://www.latinmail.com. Gratuito, latino y en espa�ol.
*
* 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/
