 |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
RE: st: Mlogit and gllamm
Arne,
Thanks for the heads up. Yes, I only really have two levels at this stage. I'll have a look at mixlogit. My preliminary models are taking upwards of 2 hours to run, and there are only a few thousand obs.
Bret
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Arne Risa Hole
Sent: Thursday, July 03, 2008 4:31 AM
To: [email protected]
Subject: Re: st: Mlogit and gllamm
Bret,
If your model has only two levels, i.e. it is a standard random effects type model, you could use my -mixlogit- module wich was published in Stata Journal 7(3). If you don't have access to the journal you can download a pre-publication draft from my website <http://www-users.york.ac.uk/~ah522/home.htm>.
-mixlogit- uses simulation rather than quadrature to approximate the likelihood function which is faster if you have more than 3-4 alternatives in your model.
Arne
2008/7/2 Howrey, Bret T. <[email protected]>:
> Listers,
>
> I need to run mlogit, multilevel models on panel data. There does not appear to be an easy way to fit this outside of gllamm. So, two questions:
>
> 1. Is there another way (gllamm is wonderfully versatile but wee bit
> resource intensive) 2. If I have to use gllamm, do the data have to be in expaned form?
>
> Appreciate any thoughts
> Thanks
> Bret
>
> *
> * 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/
*
* 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/