Date:         Tue, 22 Jan 2008 19:41:12 -0800
Reply-To:     xiaochuan.zheng@GMAIL.COM
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         xiaochuan.zheng@GMAIL.COM
Organization: http://groups.google.com
Subject:      need help with Heckman model
Comments: To: sas-l@uga.edu
Content-Type: text/plain; charset=ISO-8859-7

I was trying to address the self-selection or reverse causality
problem using the Heckman (1979) two step treatment effects model. I
ran the test by immitating the following sas codes. However, I can not
figure out how to get the coefficent & esitimate of the inlf in the
second model (see below) and the Heckman¢s ë.

proc qlim data=mroz;
model inlf = nwifeinc educ exper expersq age kidslt6
kidsge6 /discrete;
model lwage = educ exper expersq / select(inlf=1);
run;

Could anyone help? Thanks a lot.