Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Lorenzo Ciari <lorenzo.ciari@learlab.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: AW: predicted probabilities after probit |
Date | Tue, 29 Jun 2010 18:48:20 +0200 |
Il 29/06/2010 18.31, Martin Weiss ha scritto:
<> Of course I could see how you would obtain this result manually: ************* webuse laborsup, clear ivprobit fem_work fem_educ kids (other_inc = male_educ) margins, at((min) fem_educ (mean) other_inc kids) /// at((max) fem_educ (mean) other_inc kids) /// coefl post predict(pr) lincom _b[2._at]-_b[1bn._at] ************* Whether this is a valid result, I am not sure. There is probably a reason why the authors of -prchange- (part of the spost suite of commands) J. Scott Long and Jeremy Freese have not extended their command to support -ivprobit-... HTH Martin
-----Ursprüngliche Nachricht----- Von: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Lorenzo Ciari Gesendet: Dienstag, 29. Juni 2010 16:49 An: statalist@hsphsun2.harvard.edu Betreff: st: predicted probabilities after probit Dear users, I am estimating an IVprobit model, and I would like to estimate how the probability of (outcome==1) changes when a regressor goes from min to max and all the rest are unchanged. Essentially, that is done by prchange in probit. Do you know how to do it in IVprobit? Thank you. Lorenzo * * 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/ * * 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/
* * 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/