Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: RE: Binary & continuous endogenous vars


From   "Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: RE: Binary & continuous endogenous vars
Date   Sun, 29 Apr 2007 01:10:04 +0100

Richard,

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Richard Williams
> Sent: 29 April 2007 01:44
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: RE: Binary & continuous endogenous vars
> 
> At 06:03 PM 4/28/2007, Schaffer, Mark E wrote:
> 
> > > But is it legit to use ivreg for X4, e.g. do something like
> > >
> > > ivreg x4 x2 (x3 = x1 x2)
> >
> >Google and ye shall find:
> >
> >http://www.stata.com/statalist/archive/2004-07/msg00710.html
> >
> >http://www.stata.com/statalist/archive/2004-09/msg00337.html
> >
> >http://www.statacorp.com/statalist/archive/2005-07/msg00322.html
> >
> >http://www.stata.com/statalist/archive/2004-09/msg00339.html
> >
> >http://www.datasets.org/statalist/archive/2007-04/msg00415.html
> >
> >Short answer: "yes".
> 
> Impressive list!!!  Thanks.  Slightly longer answer seems to 
> be that there may be advantages to sometimes using cdsimeq or 
> treatreg too?

It's the usual efficiency-robustness tradeoff.  If you're willing to
assume normality etc., you'll get a more efficient estimator; but if
your assumptions are wrong, then it won't even be consistent.

The procedure that Wooldridge suggests (see the post by Jean Ries) is a
good alternative; more efficient than straight IV and just as (?almost
as? need to check Wooldridge) robust.  The downside is that if your eqn
is overidentifed, you won't get an overid stat from it; but you just
could use the overid stat from straight IV.

Cheers,
Mark


> -------------------------------------------
> Richard Williams, Notre Dame Dept of Sociology
> OFFICE: (574)631-6668, (574)631-6463
> HOME:   (574)289-5227
> EMAIL:  Richard.A.Williams.5@ND.Edu
> WWW:    http://www.nd.edu/~rwilliam
> 
> *
> *   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/
> 

*
*   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