st: Comparing interaction terms in simultaneous equations

[Steve Binggeli <binggeli.steve@gmail.com>]

Hello,

I am using cmp to perform simultaneous regressions for panel data.
I have two equations, same model, but different outcomes:
The two dependent variables are "job desirability" for boys and girls.
Hence, it is the same measure but repeated for two different targets.
The predictors are gender, ethnicity (dummy, 0-1) and their interaction term.

In this particular case, I was wondering whether comparing the two
interaction terms across equations (with a Wald test) could be
considered as a test of a three-way interaction (gender x ethnicity x
gender of children (boys vs girls)? If not, what would the result of
this test mean?

Ideally, I would also like to get the predicted margins from the two
interactions terms (across equations) to compare them.
Do you know how I could obtain those margins?

Here is the cmp command that I am using:

 xi: cmp (girljob = gender##ethnicity  ///
  i.parents  ses || participantid:) ///
 (boyjob =  gender##ethnicity  ///
  i.parents  ses || participantid:), cluster(participantid) ind( 1 1)
redraws(101) difficult

Thanks for your help!

Best.

Steve
*
*   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/