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

Re: st: Sargan's difference test


From   "Mark Schaffer" <M.E.Schaffer@hw.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Sargan's difference test
Date   Wed, 13 Nov 2002 16:25:56 -0000

Kai,

Date sent:      	Wed, 13 Nov 2002 16:35:21 +0100
From:           	Kai Kirchesch <kirchesch@gmx.de>
To:             	statalist@hsphsun2.harvard.edu
Subject:        	st: Sargan's difference test
Send reply to:  	statalist@hsphsun2.harvard.edu

> I am using the xtabond command for GMM estimation. However, the results 
> only report the Sargan statistic.
> Is there any possibility to perform the Sargan's difference test with Stata?
> Thanks,
> Kai

If you are using xtabond, can you not estimate the constrained and 
unconstrained versions of the equation and take the difference of the 
two Sargan statistics?

This should be correct asymptotically, but you may run into the 
problem of a negative test statistic, akin to the negative Hausman 
test statistic that was discussed on the list last week.  Even this 
can probably be easily solved with the xtabond one-step Sargan 
statistic by using the same error variance (presumably from the more 
efficient estimation) for the two Sargan stats before taking the 
difference.

--Mark

Prof. Mark E. Schaffer
Director
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
http://www.som.hw.ac.uk/cert
*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index