Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: nested logit model - estimate


From   Annalisa Marini <annalisa.marini@bristol.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   st: nested logit model - estimate
Date   Mon, 16 Mar 2009 09:40:56 +0000

Dear all,

I am estimating a nested logit model by using stata 10, which seems the most appropriate version to estimate random utility models.

I have 5 limbs and for each limb there are 2 branches, whose choice depends on both alternative-variant regressors and alternative-invariant regressors (i.e. mixed logit).

I can get the correct specification for the tree structure, but I cannot find the exact syntax for the equation to estimate and there are no examples for the mixed logit.

Moreover, I should set the alternative-variant coefficients equal for the branches in each nest. Is there a way to tell stata this?

Finally, it seems that I cannot use different weights for the individuals, because I always get a message that all the weights should be equal across individuals. This seems more a message for stata 10, because I tried in version 8 and I could use different weights.

Is there a way to solve these problems or rather should I start to think to program myself the maximum likelihood?

If anyone can help me it would be really appreciated.

Many thanks.

Best wishes,

Annalisa



----------------------
Annalisa Marini
Department of Economics
University of Bristol
8 Woodland Road
Bristol BS8 1TN
United Kingdom

e-mail: annalisa.marini@bristol.ac.uk
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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