Following xtreg, estimated with the fixed effects option fe, one can ask for xttest2. This calculates a Breusch-Pagan multipler test for the cross-sectional independence of residuals. The test is a chi-square test. If it fails, this suggests that there are contemporaneous correlations among the groups at a given point in time. The significance tests in fixed effect estimation depend on their absence. To install the test, type findit xttest2, and follow instructions. David Greenberg, Sociology Department, New York University.
----- Original Message -----
From: Mark Gasiorowski <[email protected]>
Date: Saturday, August 10, 2002 2:49 pm
Subject: st: contemporaneous correlation in panel models
>
> My previous posting seems to have gotten garbled. Sorry. Here
> it is again:
>
>
> I would like to test for contemporaneous (or cross-sectional)
> correlation in a panel model. I am estimating this model on an
> unbalanced dataset where the number of units is much larger than
> the number of time points, so I cannot use FGLS or PCSE models to
> deal with contemporaneous correlation. Does anyone know how I
> can do such a test, either in LIMDEP or in Stata? Also, I do not
> have a good feel for how much and what sort of a problem
> contemporaneous correlation poses, so I would appreciate learning
> of any citations that might discuss it in detail. Thanks.
>
> Mark Gasiorowski
> Department of Political Science
> Louisiana State University
> Baton Rouge, LA 70803 USA
> Phone: (225) 578-2550
>
>
> *
> * 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/
