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

st: data format for MNP estimation using "asmprobit"


From   hyeok jeong <hjeong@usc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: data format for MNP estimation using "asmprobit"
Date   Mon, 19 Sep 2005 16:44:57 -0700

Dear Statalist:

I am trying to use "asmprobit" to estimate a multinomial probit occupational choice model with four or possibly five alternatives.
This is my first try for both use of the "asmprobit" and the use of MNP model.
Reading the manual, I found that "asmprobit" requires that the data be formatted such that each decision-maker (case) should be assigned to multiple possibilities of all alternatives for some variables, the so-called alternative-specific variables.
As far as I know, what we need for identifying MNP model is some set of proper "exclusion restrictions," (as illustrated by Keane (1992)), not the suggested format of the data itself. (And suppose I do have some meaningful exclusion restrictions.)
Neither "mprobit" (although it is not useful for the case with general covariance structure) nor "mlogit" (again not useful when IIA assumption is not valid) seem to require such data format So, I do not understand why such data format for asmprobit is required. I don't know if simply expanding the data solves the problem...

I will appreciate a lot if anyone can explain why we need this data format and if there is any way to get around this problem.

Thank you very much.

Hyeok
*
*   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