Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Nora Reich <nhmreich@googlemail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: simultaneous equations: probit and ordered probit |
Date | Tue, 20 Mar 2012 17:30:23 +0100 |
Dear stata users, I would like to estimate simultaneously a probit model and an ordered probit model, as the dependent variables are assumed to be determined simultaneously, or, as each dependent variable might influence the other. I have found a threat about this in the archives, but it seems that the person with the same question in 2006 did not receive any advice (http://www.stata.com/statalist/archive/2006-07/msg00262.html). I first wanted to use -cmp- (conditional mixed process) but now I have read: "...cmp can only fit "recursive" models with clearly defined stages, not ones with simultaneous causation. A and B can be determinants of C and C a determinant of D--but D cannot be adeterminant of A, B, or C. And the "conditional" means that the model can vary by observation." ( http://www.stata.com/statalist/archive/2007-10/msg00646.html) Therefore, it seems that in my case, C and D should be determined simultaneously, whereas in -cmp- models, there is no simultaneous estimation and D should not affect C. Does anyone have a suggestion for an alternative model I could use? Thanks in advance Nora Reich -- Nora Reich Publications: http://www.hwwi.org/ueber-uns/team/forscher/nora-reich/publications.html * * 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/