hello, once again...let me apologize for sending a very general question on
unbalanced data. i have had a further look into the problem and i am
beginning to understand what unbalanced data means. i would, however,
appreciate any references on nested logits with unbalanced data if you know
of any.
thank you,
marina
-----Original Message-----
From: [email protected]
[mailto:[email protected]]On Behalf Of Marina Fe B.
Durano
Sent: Thursday, August 21, 2003 9:17 PM
To: [email protected]
Subject: st: nested logit on pooled data
hello!
i am trying to estimate a choice of destination country for migrants using a
nested logit model on data pooled from surveys over 7 years. there are two
levels. the top-level nests (to migrate or not) have demographic
characteristics of the individuals for explanatory variables. the
bottom-level nests contain the destination countries. one of the nests at
the bottom level is degenerate with only one country for those who chose not
to migrate. the second nest has all the countries where the migrants went.
the bottom level has country-specific characteristics as the explanatory
variables (generic) and the country-specific dummy variables.
when i ran the nested logit, i received an "unbalanced data" error message.
can anyone tell me what this means in my situation? how do i resolve this
problem? i did not encounter this problem when i ran the nested logit on one
year's cross section.
i was able to estimate the two levels separately. the top level was
estimated as a logit model while the bottom level was estimated as a
conditional logit model.
much thanks in advance,
marina
Marina Fe B. Durano
Dover St. Building, Room N.3.10
School of Economic Studies
University of Manchester
Manchester M13 9PL
United Kingdom
Tel: +44(161)2754516
Fax: +44(161)2754928
*
* 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/
