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: Margins after cmp mprobit


From   Alfonso Sanchez-Penalver <[email protected]>
To   Stata List <[email protected]>
Subject   st: Margins after cmp mprobit
Date   Sun, 23 Mar 2014 10:32:08 -0400

Hi everyone,

I am using Stata 13.1 on a mac, and I am running a Heckman multinomial probit using -cmp- (SJ, SSC) and I’m trying to get the marginal effects on the probabilities of all the choices. The syntax I use for the -cmp- command is the following

cmp (MultiGive = $x2, iia) (FamGiveDum = $x2), ind(FamGiveDum*$cmp_mprobit $cmp_probit) vce(cluster StateID) qui

The problem I’m having is with the marginal effects on the probability of the first choice in the multinomial probit, i.e. the one that -cmp- takes as the base option. It simply returns zero for all marginal effects. The syntax I’m using to try and get to these marginal effects is

margins, dydx(*) predict(eq(_outcome_1_1) pr)

For the other two possible outcomes and for the selection equation I have no problem in getting the marginal effects, but for that one it doesn’t.

Any suggestions?

Alfonso Sanchez-Penalver

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


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