With just ten units and 20 annual observations, you shoul be thinking of doing panel-corrected standard error estimation with xtpcse. It will allow you to take into account correlations among the errors. It does not offer a robust option.
- David Greenberg, Sociology Department, New York University
----- Original Message -----
From: Kimberley Tran <[email protected]>
Date: Tuesday, October 14, 2003 2:14 pm
Subject: st: Fixed Effects Model
> Greetings Everyone,
>
> My empirical estimation is based on a panel of 10 units for a 20-
> year time
> period.
> I have reasons to believe that the model is a fixed effect model.
> My question
> is: are there commands to test for, and correct autocorrelation
> and
> heteorscedasticity in a fixed-effect model? Furthermore, is the
> "robust"
> command in Stata valid for panel data? I keep getting an "invalid
> syntax"
> message.
> I thank you for your time, and anxiously await suggestions!
>
>
> cheers
> Kimberley
>
> *
> * 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/
>
*
* 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/
