st: re: heteroskedasticity and fixed effects

[Kit Baum <baum@bc.edu>]

<  >

Alice wrote

I was wondering which test or command I should be
using. I found the xttest3 that can be used after
xtreg, or whitetst after reg.

I was wondering whether those tests would be reliable,
assuming that Stata 10 does adjust standard errors
correctly.


xttest3 (which I wrote) only makes use of the residuals from xtreg,  
fe. Like any test based solely on residuals, it is immune to  
inconsistency in the correlation of the coefficients' standard  
errors. It will return the same value regardless of the choice of vce 
(). However, note that it tests for a specific sort of H: groupwise H  
(q.v. -robvar-).  It is not a general test for H of the Breusch-Pagan  
sort.

You may want to explore use of -xtgls- if you are concerned about  
other kinds of H in your particular setting.

Kit

Kit Baum, Boston College Economics and DIW Berlin
http://ideas.repec.org/e/pba1.html
An Introduction to Modern Econometrics Using Stata:
http://www.stata-press.com/books/imeus.html


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/