Thanks Allen! Only one question more please.
Does someone know about a command that takes into account at the
same time fixed effects and heteroskedasticity across panels?
I have used xtgls but as Allen rightly says it doesn't consider fixed effects.
I know xtregar considers fixed effects and only autocorrelation within panels.
Your help will be appreciated a lot.
Thank you!
Allen McDowell wrote:
>-xtgls- does not fit fixed effects models. Rather, it is an implementation >of a generalized least squares estimator that can account for error >terms that are not identically or independently distributed across panels
>and for cases where the errors are autocorrelated within panel.
Paula Garcia wrote:
> I have a doubt on panel data and I would be very grateful if someone
> could give me some insights. When you estimate using xtgls, the error
>term e, does include the fixed effects v? I think that they are not
>included, but then, is it a model on panel data without considering the
>fixed effects, like in xtreg, for example?
_________________________________________________________
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/
