Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

st: xtdpd: efficiency, consistency


From   Ari Dothan <ari.dothan@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: xtdpd: efficiency, consistency
Date   Tue, 28 Dec 2010 18:50:02 +0200

Hi all,

When I run the regression using "twostep  hascons vce(robust)" I get
in some cases a rather large standard error, which renders the
coefficient insignificant. Abond test is, naturally,  OK.
When I run the same regression using "twostep  hascons" (without the
robust error specification), I get highly significant results, but in
many cases estat sargan rejects.
I tried many variants of instruments, but cannot change the
specification because this is the model I am testing.
Naturally, the coefficients in both types of regressions are identical.
It is clear that I have an efficiency problem.
My question is whether I can claim that the solution is consistent:
(A) due to the fact that coefficients obtained in both types of
regressions are identical, and (B) due to the fact that I have some
several thousand observations supporting it.
Your input will be much appreciated
Happy holidays to all
-- 
Ari Dothan
*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index