[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: Multilevel and gllamm
Then at least theoretically you should first attempt to model the
overdispersion at zero, like in zero-inflated Poisson models, or in
Tobit and related models, and then the remaining stuff. I am not sure
if that is easily done with -gllamm-. You would then need to play
around with mixed responses and -fv- option, probably. I have never
explored this so far.
Sorry to leave you confused more than you were when you first posted this
I'll look into these issues. Thank you.
* For searches and help try: