st: RE: xtabond2 Sargan and Hansen test

[DE SOUZA Eric <eric.de_souza@coleurope.eu>]

See the paper by the author of xtabond2, David Roodman: how to do xtabond2. It can be found at http://www.cgdev.org/content/publications/detail/11619

See especially Section 2.5 The Sargan/Hansen test of overidentifying restrictions 
and the beginning of the next section on Too Many Instruments

You will find a complete discussion there.

Eric


Eric de Souza
College of Europe
BE-8000 Brugge (Bruges)
Belgium

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Flora Hofmann
Sent: 17 April 2010 11:38
To: statalist@hsphsun2.harvard.edu
Subject: st: xtabond2 Sargan and Hansen test

Dear Statlists, 

I am confused about the Sargan and Hansen tests reported after xtabond2 in the case of onestep, robust system GMM estimation. In the case of non-spericity in the errors the Sargan test is inconsistent and the Hansen test based on the twostep estimates is prefered. 

If I understood correctly, considering this xtabond2 reports the hansen statistic based on the twostep estimates in this case. Is that to say that the test statistic reported under 'Sargan test of overid. restrictions' is the hansen test from the twostep estimates? And if that is the case what is reported under 'Hansen test of overid. restriction'?

I am sorry if I am bothering you with an 'obvious' question.

Best
Flo Hofmann




-- 
GRATIS für alle GMX-Mitglieder: Die maxdome Movie-FLAT!
Jetzt freischalten unter http://portal.gmx.net/de/go/maxdome01
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/