Re: st: mfx in ssm

["Anders Alexandersson" <andersalex@gmail.com>]

ssm calls gllamm. gllapred (not predict) is the prediction command for
gllamm. I'm not sure what Jenny means by "marginal fixed effect" but
maybe the gllapred options marginal and mu, and/or the command mfx2
rather than mfx would work for her.

Anders Alexandersson
andersalex@gmail.com

Jenny S�ve-S�derbergh <Jenny.Save-Soderbergh@sofi.su.se> wrote:

> I have a problem when I run a ssm model using the following
> command (ordered probit with sample selection):
>
> ssm risk fem marriem marriedf cohab cohabf,
> s(active= fem age age2 edu1 edu3
> wage nofin pension) q(15) adapt family(bin) link(oprobit) sel
>
> I then would like to predict probabilities for the three outcomes that
> are included in the dependent variable (risk=1,2,3). But when I try
> to use "predict" I am only able to specify one category! Moreover, I
> would like to obtain marginal fixed effects for the three outcomes.
>
> Does anyone have a suggestion?
*
*   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/