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

Re: st: Nested logit with shares/grouped data


From   vwiggins@stata.com (Vince Wiggins, StataCorp)
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Nested logit with shares/grouped data
Date   Wed, 09 Nov 2005 11:01:30 -0600

Peter Wright <Peter.Wright@nottingham.ac.uk> asks about estimating a
nested-logit-type model where the dependent variable is a count of positive
outcomes for each alternative or a proportion for each alternative.  Peter
notes that there is a FAQ that describes how to do this with logistic or
multinomial logistic models at,

      http://www.stata.com/support/faqs/stat/grouped.html 

The method described in the FAQ will indeed work for -nlogit-, but that is not
going to help Peter.  There is a crucial difference between his data and the
data described in the FAQ.  Peter has what I usually call summary data.  That
is to say, both his dependent and independent variables are themselves
averages.  The FAQ describes data where we know the values of the independent
variables for each case, they are just repeated for many cases, and we know
only that a certain number of cases fall into each alternative.

Stata does not currently have an estimator for nested logit models applied to
summary data and the method described in the FAQ is not appropriate for such
data.


-- Vince
   vwiggins@stata.com

*
*   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