Date:         Sun, 6 Aug 2006 16:05:28 -0700
Reply-To:     BruceBrad <b.bradbury@UNSW.EDU.AU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         BruceBrad <b.bradbury@UNSW.EDU.AU>
Organization: http://groups.google.com
Subject:      Re: Logistic regression with instrumental variables?
Comments: To: sas-l@uga.edu
In-Reply-To:  <ctmsc2pqaiqjcsco8paflmlt80m3ebi6gn@4ax.com>
Content-Type: text/plain; charset="iso-8859-1"

> Are there any SAS tools to do IV analysis with binary outcomes?

I don't think so. Angrist and Krueger in their survey argue that 2SLS
is still a robust means of estimating an average treatment effect when
the dependent or IV variable is binary.

Angrist, Joshua D. and Alan B. Krueger (2001), 'Instrumental
variables and the search for identification: From supply and demand to
natural experiments' Journal of Economic Perspectives 15:69-85.