Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: heteroskedasticity problem in panel

From   parisa <>
Subject   st: heteroskedasticity problem in panel
Date   Sun, 29 Apr 2012 07:58:13 -0700 (PDT)

I 'd like to get some expert advice on heteroskedasticity in panel data. 
I have an unbalanced panel with N=20 group and T=28 time period. 
I  followed the heteroskedasticity test described in the FAQ using xtgls 
( ) . 

The following test I have done: 
xtgls depvar indvars, igls panels(heteroskedastic) 
estimates store hetero 
xtgls depvar indvars 
local df = e(N_g) - 1 
lrtest hetero  . , df(`df') 


(log-likelihoods of null models cannot be compared)
Likelihood-ratio test                                  LR chi2(12) =   
(Assumption: nohetero nested in hetero)                Prob > chi2 =   

So I clearly have a heteroskedasticity problem. But I have two questions:
1-What is the meaning of the first sentence in the test result
(log-likelihoods of null models cannot be compared)?
2-how to correct for heteroskedasticity in panel data except GLS (xtgls
depvar indvars, igls panels(heteroskedastic))?
Thank you 

View this message in context:
Sent from the Statalist mailing list archive at
*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index