st: RE: RE: RE: RE: RE: Is Hansen test in XTABOND2 really robust?

["Ruiqing Miao" <ruiqingmiao@gmail.com>]

Thank you, Eric.
Ruiqing

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of DE SOUZA Eric
Sent: Friday, November 01, 2013 11:41 AM
To: 'statalist@hsphsun2.harvard.edu'
Subject: st: RE: RE: RE: RE: Is Hansen test in XTABOND2 really robust?

Since I have always used -xtabond2- and have never used the dynamic panel data estimation commands that come with Stata, nor have I read the correspondig pages in the manual , I cannot answer your questions.


Eric de Souza 
College of Europe 
Brugge (Bruges), Belgium 
http://www.coleurope.eu




-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Ruiqing Miao
Sent: 01 November 2013 16:55
To: statalist@hsphsun2.harvard.edu
Subject: st: RE: RE: RE: Is Hansen test in XTABOND2 really robust?

Hi, Eric, thank you very much for your help. I think your quote from "How to do xtabond2" explains why the Hansen test in -xtabond2- is the same as the Sargan test in twostep -xtabond-. But when I include both "twostep" and "vce(robust)", the Stata will reports "cannot calculate Sargan test with vce(robust)". Does this mean that the Sargan test from the twostep -xtabond- is not robust? Moreover, could you please give me some hints on why  " performing the Sargan test after the two-step estimator is an alternative" that is stated in Stata manual (the manual for �xtdpdsys postestimation � Postestimation tools for xtdpdsys�, page 107 in Stata 11)?

Bests,
Ruiqing

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of DE SOUZA Eric
Sent: Friday, November 01, 2013 10:24 AM
To: 'statalist@hsphsun2.harvard.edu'
Subject: st: RE: RE: Is Hansen test in XTABOND2 really robust?