[R] (no subject)

jruiz99@ensae.org jruiz99 at ensae.org
Tue Nov 30 16:55:27 CET 2004


I am trying to estimate a choice model with varying choice set for each

I would like to fit different kinds of model (logit ,nested logit,

So far I have found that package *mnp* allows me to estimate a probit model
with varying choice set.

But for estimation of a logit model, I have only found function *multinom*
of package *nnet* which does not seem to allow for varying choice set.

I could incorporate indicators of choice availability as explanotary
variables, but it does not seem a very good way to do it.
Instead, for a logit model, I have coded a likelihood computation of the
underlying model with varying choice set and I use optim function to get
the "maximum".

I wondered if there were more user friendly functions available and/or
other choice model related package.


More information about the R-help mailing list