Jan Sauermann <[email protected]> asked:
> I estimated the following recursive bivariate probit model
>
> y1 = x1 + x2 + x3 + y2
> y2 = x1 + x2
>
> y1, y2, x1 and x3 are binary, x2 is a metric variable. I want to
> use the -margeff- ado-file to compute marginal effects and the
> corresponding standard errors. The syntax for -margeff- should be
>
> margeff compute, at(mean x1 = 1 , x3 = 1) model(biprobit)
>
> However, stata produces "invalid syntax r(198);". -margeff- after a
> simple probit model produced correct marginal effects.
Right now, margeff does not support recursive bivariate probit models.
(The reason is simple: I had some programming difficulties with that sort of model.)
There is a minor but in margeff that prevents it from issuing an error message
that tells the users that recursive models are not supported and mfx should be used.
Tamas
(author of margeff)
------------------------------------------------
Tamas Bartus, PhD
Associate Professor, Institute of Sociology and Social Policy
Corvinus University, Budapest
1093 Budapest, Fovam ter 8.
Phone: +36-1-482-5290 Fax: +36-1-482-5226
Homepage: www.uni-corvinus.hu/bartus
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
