[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: gnbreb first differences
I am wondering if code has been devleoped that will allow for Clarify-like
first differences or relative risks to be generated from the gnbreg model
(Clarify supports the negative binomial, but not the generalized form).
Obviously the predict command works, but I need to develop predictions for
various combinations of x[i]s.
One suggestion I have seen is to use the "mfx" command; is there an
intuitive interpretation of these results?
Other suggesitons welcome.
Erin M Simpson
* For searches and help try: