In the help for contrast, the Stata manual says
Is there any way user-written routines can add support for _eqns? For example, the following commands work fine:
But, when I try to do the same thing with my gologit2 program,
I get the message
It would be nice if there was some little ereturn I could add to gologit2, but if so I don't know what it is. if the supported programs are hard-coded in to contrast, I guess I am out of luck.
_eqns designates the equations in manova, mlogit, mprobit, and mvreg and can be specified anywhere a factor variable appears.
Code:
webuse nhanes2f, clear mlogit health i.race c.age i.race#c.age contrast i.race#c.age#_eqns
Code:
gologit2 health i.race c.age i.race#c.age contrast i.race#c.age#_eqns
Code:
. contrast i.race#c.age#_eqns
variable _eqns not found
