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

st: Query: Nested-logit


From   siyama@who.int
To   statalist@hsphsun2.harvard.edu
Subject   st: Query: Nested-logit
Date   Thu, 10 Jul 2003 17:20:51 +0200

Dear Stata listers, 

I hope I get third-time lucky with posting this  query. A colleague of mine
is trying to run a nested logit on the following :

Level 2 - did you seek health care.... (Yes / No),  if yes,  Level 1 -  From
which type of provider  (Private / Public). 

After rearranging the data set, she can obtain the following "nlogittree"
output

 nlogittree choices type
 tree structure specified for the nested logit model
         top --> bottom
         type       choices  
 --------------------------
        type1        Public  
                        Private  
        type2       No Care 

Following on to the nlogit model 

.xi:nlogit chosen (choices = i.sex X2 X3) (type = i.sex X2 X3),  group(hhid)
 i.sex             _Isex_1-2           (naturally coded; _Isex_1 omitted)
 tree structure specified for the nested logit model
         top --> bottom
        type       choices  
--------------------------
        type1        Public  
                        Private  
        type2       No Care  
unbalanced data
 r(459);
 

 Could the "unbalanced data" error be borne out of the lack of alternatives
beyond "Seek Health Care == No Care", or is more to do with a data
restructuring/ management issue.


Many thanks for your thoughts and suggestions in advance.


 Amani
*
*   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