Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: random effects, heteroskedasticity & autocorrelation

From   "Mark Schaffer" <>
Subject   Re: st: random effects, heteroskedasticity & autocorrelation
Date   Wed, 12 May 2004 13:09:38 +0100


Date sent:      	Wed, 12 May 2004 12:01:04 +0100
From:           	Cordula Stolberg <>
Subject:        	st: random effects, heteroskedasticity & autocorrelation
Send reply to:

> Dear all,
> I have two questions with regard to a random effects model. How do I test 
> for heteroskedasticity and autocorrelation in such a model? I know I can 
> use xtgls if there is heteroskedasticity and / or autocorrelation, but I 
> don't know how to detect it.
> Moreover -and this might be a very silly question- if I have a random 
> effects model and the Hausmann test tells me that the random effects is 
> better than fixed effects, how come that the results improve when I include 
> country dummies in the random effects regression (the countries would have 
> been the fixed effects)?

With respect to your second question, I think you might find that by 
including the country dummies, your random effects estimation has 
degenerated into pooled OLS.  You can tell by checking whether the 
sigma_u that is reported by xtreg is zero.

Hope this helps.


> Thanks for your help,
> Cordula
> *
> *   For searches and help try:
> *
> *
> *

Prof. Mark E. Schaffer
Centre for Economic Reform and Transformation
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS  UK
44-131-451-3494 direct
44-131-451-3008 fax
44-131-451-3485 CERT administrator
*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index