Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Marginal Effects in a Seemingly Unrelated Biprobit


From   "Murasko, Jason Elliot" <jmurasko@iusb.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Marginal Effects in a Seemingly Unrelated Biprobit
Date   Wed, 11 May 2005 12:48:38 -0500

Statalist,
 
I am using a seemingly unrelated biprobit analysis to address an endogeneity problem. I am estimating a model of the general form:
 
Y1 = a + bX + cY2 + u
Y2 = d + eX + fZ + v
 
where Y2 is endogenous, Z is an instrument, and u and v are not independent.
 
I want to compare marginal effects from the first equation in this system to a univariate probit of the same form (which ignores the endogeneity of Y2). That is, I want to compare the marginal effect of Y2 in both the biprobit and simple probit models. 
 
Which predict option is most suitable for this analysis? Specifically, what is the difference between the p11, pmarg1, and pcond1 predictions and their implications for marginal effects?
 
Thank you,
 
Jason E. Murasko
School of Public and Environmental Affairs
Indiana University South Bend

*
*   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