Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: censored probit with multinomial and ordered outcomes


From   David Quinn <dxquinnx@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: censored probit with multinomial and ordered outcomes
Date   Fri, 4 Feb 2011 18:01:08 -0500

Hello,

I would like to run a censored probit model to assess possible
endogeneity/selectivity for several outcome variables, one of which is
multinomial and the other of which is ordered.  Is there a
procedure/function in STATA that will allow me to do so?  I know of
"heckman" and "heckprob," but those can only be used for continuous
and binary outcomes, respectively.  And "tobit," but that's also only
for continuous outcomes.

I also know of several STATA commands that were written to implement
approaches for assessing endogeneity when the selection equation is
multinomial (Lee, Dubin and McFadden, etc.): "svyselmlog,"
"mtreatreg," and "selmlog."  But again, none of these can be used when
the outcome equation is multinomial or ordered, implementing something
along the lines of what William Greene (2006) discusses.

Perhaps I've overlooked something, so I'd appreciate any insight that
folks have on the matter.  In sum, I'm looking for a procedure that
will allow me to run censored models wherein the outcome equations are
multinomial and ordered, and the selection equations are binary,
multinomial, and ordered.

Thanks in advance for any insight that you can provide,
--David
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index