Statalist


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

Re: st: RES: treatreg model with binary outcomes


From   "Austin Nichols" <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RES: treatreg model with binary outcomes
Date   Tue, 20 Nov 2007 11:49:14 -0500

..
See also
http://www.stata.com/statalist/archive/2004-12/msg00321.html
on the use of -biprobit- plus an alternative (Abadie 2003) that would
be easy to translate to Mata.  See also Angrist 2000:
http://www.nber.org/papers/t0248

On 11/20/07, Austin Nichols <austinnichols@gmail.com> wrote:
> There is a serious flaw in that two-step logit model--it is not
> consistent, and is an example of what Wooldridge (2002) calls the
> "forbidden regression" (see section 15.7.3, pp.477-478).  That same
> section discusses the MLE for probit with a binary endogenous
> variable.
>
> Wooldridge, J.M. 2002. Econometric Analysis of Cross Section and Panel
> Data.  Cambridge, MA: MIT Press.
*
*   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