Thank for the tip Nick,
I have looked it up but again is not what I am looking for. Both nlogit and
nlogitrum use the clogit type of data. That is you have observations on the
characteristics of the alternatives (let's say n alternatives). For every
decision makers you have n observations recording the caracteristics of the
alternatives for that particular decision maker and one varaible that
records the chosen alternative.
I have mlogit type of data. One observation per decision maker, the
variables record the characterisitcs of the decision maker (her age, income,
educational level, occupation....) plus one varaible recording the chosen
alternative.
I would like to know whether someone has developed a routine to estimate a
nested logit model from this type of data.
Thanks again
Giovanni
-----Oorspronkelijk bericht-----
Van: Nick Cox [mailto:[email protected]]
Verzonden: maandag 7 oktober 2002 17:58
Aan: [email protected]
Onderwerp: st: RE: Nested logit
Russo, Giovanni
>
> I am looking for a routine for the estimation of a nested
> logit model. I
> have data on job seekers choosing the search method. I observe the
> characteristic (age, gender, income, educational levlel) of
> the decision
> makers and the alternative chosen. This is a "mlogit" type
> of data rather
> than the clogit type of data used by the nlogit command in
> Stata. In the
> latter case one observes the characteristics of the
> alternatives; the
> decision makers are not important.
There is an article in the latest Stata Journal on
random utility maximization nested logit, which may
help. You can download the software
from within Stata.
Nick
[email protected]
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
