[Limdep Nlogit List] user-specified marginal effects in ordered probit

[Philip A. Viton]

(limdep 8): can one specify a point at which the marginal effects in 
the ordered probit model are evaluated? If so, can anyone see what 
what am I doing wrong here? The result appears to be the same, no 
matter whether margin=mniv is used or not.

namelist;iv= ... $
ordered;lhs=abc;rhs=iv;margin$

matrix;mniv=0.7 * mean(iv)$ ? mniv = 70% of the means
ordered;lhs=abc;rhs=iv;margin=mniv$

Imitating the online help file and creating a point by

matrix;xo=[1,2,3,4,5 ...]$

and then : ordered;lhs=abc;rhs=iv;margin=xo$
also seems to make no difference.


Thanks!


------------------------
Philip A. Viton
City Planning, Ohio State University
275 West Woodruff Avenue, Columbus OH 43210
viton.1 at osu.edu