[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Multinominal Logit

From   "Xiaoheng Zhang" <>
Subject   Re: st: Multinominal Logit
Date   Wed, 22 Aug 2007 13:12:47 +0100

hi Killian,

Sounds like you are going to do a discrete-choice model.A simple
suggestion is that if your explanatory variables contain
payment-specific characteristics(I guess,such as costs and service
providers), you need to use the Conditional Logit Model; if your
explanatoiry variables only contain individuals' characteristics, you
can use the Multinominal Logit (or the Conditional Logit,it yields the
same outcomes as the Mulitinominal Logit will do). My best advice for
you to start is to read State manual re. the Multinomial Logit and the
Conditional Logit,it provides very good examples on
transportation-mode choice and restaurant choice.

On 22/08/07, Killian Murphy <> wrote:
> I have survey data on payment instruments and i am attempting to determine
> what are the factors that affect an individuals decision to choose one
> payment method over another.
> Am i correct in using a multinominal logit model?
> Is the command mlogit correct
> is it possible that you could provide me with a do.file as an example
> Thanks so much for your help,
> Killian
> _________________________________________________________________
> Find a local pizza place, movie theater, and more….then map the best route!
> *
> *   For searches and help try:
> *
> *
> *


Xiaoheng Zhang (Kevin)

*   For searches and help try:

© Copyright 1996–2022 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index