Marginal Probability Effect in regoprob

[Neeraj Kumar]

Hi,
I am using regoprob command for estimation. My dependent variable having 10 categories and I am using 5 year Panel data. Is it possible to calculate marginal probability effect in the case of regoprob.
I used the following commands

 regoprob A170 quantX0472 quantX0473 quantX0474 relative2 relative3 relative4 IU0 X003 X011, i(newid)

For calculates predicted probabilities marginal on the individual effect. I used the following command

predict p1 p2 p3 p3 p4 p5 p6 p7 p8 p9 p10, p

[Fei Wang]

Neeraj, why not using -xtoprobit-?

xtset newid
xtoprobit A170 quantX0472 quantX0473 quantX0474 relative2 relative3 relative4 IU0 X003 X011
margins, dydx(*)

[Neeraj Kumar]

Hi,
Actually one of the main reason is not to use ordered probit is the parallel line assumption, usually assume that the estimated coefficients of independent variables do not vary between the categories (parallel-lines assumption, cf. Long 1997). This view neglects possible heterogeneous effects of some explaining factors. For example, the traditional ordered probit model implies that all variables are constrained and meet the parallel-lines assumption. On the other hand, a fully flexible approach (generalised ordered probit) allows all coefficients to vary across the categories. That's why I want to use REGOPROB. Sorry for late reply.