st: xtabond2: gmm( ) and consistent estimates

["ALICE DOBSON" <alice_dobson@hotmail.com>]

Hi Tim,
I was curious to know whether you got the same estimates by retaining and 
dropping the exogenous variables from the GMM portion? Further, did you 
receive any response to your posting?

Best,
Alice



Date: Tue, 21 Jun 2005 01:25:06 -0700 (PDT)
From: Tim Brown <timbrownphd@yahoo.com>
Subject: st: xtabond2: gmm( ) and consistent estimates

When using xtabond2, if some exogenous variables (or
predetermined) are omitted from the gmm() portion of
the equation (but are included in the main equation),
does this result in inconsistent estimates (as in
2SLS)or are they still consistent (as when using
generalized
instrumental variables)?

e.g.,

xtabond2 g l.g l.h l.r l.s l.m  l.incometenthou,
iv(l2.c l2.a) gmm(l.g l.h l.r l.s l.m) twostep
noconstant robust artests(4)

vs.

xtabond2 g l.g l.h l.r l.s l.m  l.incometenthou,
iv(l2.c l2.a) gmm(l.g l.h l.r) twostep noconstant
robust artests(4)

where variables s and m are omitted? Are both
estimated equations consistent or does dropping these
two variables from the gmm() result in inconsistent
estimates?

Thanks,

Tim Brown
UC Berkeley

_________________________________________________________________
Don�t just search. Find. Check out the new MSN Search! 
http://search.msn.click-url.com/go/onm00200636ave/direct/01/

*
*   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/