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

st: AW: Randon Coefficient vs Mean Group Estimation

From   "Martin Weiss" <>
To   <>
Subject   st: AW: Randon Coefficient vs Mean Group Estimation
Date   Tue, 7 Apr 2009 16:29:00 +0200


What does

mat l e(b)

give you after either model? This way, you can see whether there is overlap between the returned results after both commands.

Also: Have you paid attention to the requirements for -hausman- as detailed in -h hausman- under heading "description"? Have you looked at -suest-?


-----Ursprüngliche Nachricht-----
Von: [] Im Auftrag von Grant Peter Kabango
Gesendet: Dienstag, 7. April 2009 16:15
Betreff: st: Randon Coefficient vs Mean Group Estimation

Dear Statalist,

I am using two estimators to account for sectoral heterogeneity: the Mean Group model and Random Coefficient model.

I get my Mean Group Estimation through the Stata command 'xtpmg' with an 'mg' option; and I get my Random Coefficient estimation using the 'xtrc' Stata command. 

However, since these two estimators differ in their assumption of the nature of heterogeneity, I am using the Hausman test to check which of the two is better. Surprisingly, the test is returning with the following error message;

"no coefficients in common; specify equations (matchlist) for problems with different equation names." r(498).

What could be the problem in this case?



*   For searches and help try:

*   For searches and help try:

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