st: sequential logit model

["Jun Xu" <mystata@hotmail.com>]

Stata Listers:

I have the following setup of discrete choice (first register and then vote) 
model.  Peole make decision along the road.  They first need to choose 
between branch 1 and 2, and then those choose branch 2 go ahead making their 
second decisions of choosing either branch 3 or 4.   I am not sure if I 
could go ahead using nlogit, but it seems that I need to have choice 
specific attributes, whereas my data set contains only individual 
characteristics.  Not sure if there is any routine that can estimate the 
following model, where B and X's are specific to each decision stage.  Also, 
X1 and X2 might have some overlap.

--------branch 1: F(B1X1)
   |
   |
   |
   |
   |___branch 2: 1-F(B1X1)
                   |
                   |
                   |
                   |
                   |____branch 3:(1-F(B1X1))F(B2X2)
                   |
                   |
                   |
                   |____branch 4:(1-F(B1X1))(1-F(B2X2))

Thanks a lot.

Jun Xu
Department of Sociology
Indiana University at Bloomington



_________________________________________________________________
MSN 8 with e-mail virus protection service: 2 months FREE*  
http://join.msn.com/?page=features/virus

*
*   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/