Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: Mixed logit?


From   "Julia A. Gamas" <jgamas@mit.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Re: Mixed logit?
Date   Fri, 7 May 2004 11:12:14 -0400

Dear all,
for those of you who might be interested.  As of now Stata doesn't do Mixed
Logits but I hope it will be incorporated into future versions.  For now, if
anybody is interested, there are three venues (according to my research) as
I explain ahead.  In general, it seems to me that none of the options are
more user-friendly than Stata.  I do hope Stata will develop mixed logits.
I'm wondering if Stata couldn't create a command by "translating" Dr.
Train's code from Gauss?
Anyway, the options are:
1 ) Limdep (and Nlogit),
2) Gauss code of Prof. Train at UC Berkeley
3) Biogeme (free software) - requires running commands from DOS.
Option 2) seems to be the most powerful but requires Gauss.
Sincerely,
Julia
Integrated Program on Urban, Regional and Global Air Pollution
MIT
----- Original Message ----- 
From: "Julia A. Gamas" <jgamas@mit.edu>
To: <statalist@hsphsun2.harvard.edu>
Sent: Wednesday, May 05, 2004 4:04 PM
Subject: Mixed logit?


>
> I have two questions that I hope someone can answer for me:
> I need to do estimation using a multinomial logit model that allows for
the
> error term to be flexible; mixed logit.
> 1)  Does Stata do this type of estimation?
> 2) If so, which comand should I use?  Is xtlogit what I need?
> Any help will be greatly appreciated.
> Sincerely,
> Julia A. Gamas
> Integrated Program on Urban, Regional and Global Air Pollution
> MIT
>

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index