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

st: RE: Breusch-Pagan test and random effects estimation


From   "Mariano Alvarez" <[email protected]>
To   <[email protected]>
Subject   st: RE: Breusch-Pagan test and random effects estimation
Date   Fri, 16 Dec 2005 12:47:18 -0300

Valeriano,
The Breusch-Pagan statistic test the null that var(vit)=0, so under the null
OLS is consistent. If you accept the null, that means that you cannot
estimate the model using Random Effects. I recommend you to estimate with
Fixed Effects estimator and perform an F-test in order to evaluate the joint
significance of the specific effects (at the bottom of the regression table
appears this statistic). If you accept the null, you can conclude the
absence of specific effects, so you can use OLS.
I hope this will help you

Mariano

-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Martinez San
Roman, Valeriano
Sent: Viernes, 16 de Diciembre de 2005 05:47 a.m.
To: [email protected]
Subject: st: Breusch-Pagan test and random effects estimation

Hello all,
 
 
I have other beginer�s question. When you run a random effects estimation on
panel data, and you compute the Breusch-Pagan test for random effects.
 
If the statistic acept the null hypothesis, Can we conclude that the random
effects estimator is better than the fixed effects one?
 
Thank you very much.

*
*   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/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index