[Limdep Nlogit List] Prediction in ordered probit model

William Greene wgreene at stern.nyu.edu
Wed Oct 10 10:01:37 EST 2007


The two possibilities are (1) as listed below and (2) the
index of the cell with the largest estimated probability.
I suspect these would give similar if not identical answers,
but I've never actually checked it.
/Bill Greene
----- Original Message -----
From: "Steven Yen" <syen at utk.edu>
To: "Limdep and Nlogit Mailing List" <limdep at limdep.itls.usyd.edu.au>
Sent: Tuesday, October 9, 2007 12:02:16 PM (GMT-0500) America/New_York
Subject: [Limdep Nlogit List] Prediction in ordered probit model

How is prediction done in order probit (or logit) model? 
Specifically, how do you determine the ordinal outcome from the 
predicted linear index? The ordered probit model is characterized by

     y = j if mu_(j-1) <= x'b + u < mu_j

Upon estimation, do you simply determine the y outcome by

     y = j if muhat_(j-1) <= x'bhat < muhat_j

Thank you.



Steven T. Yen
http://web.utk.edu/~syen/
Check out our postdoc opening at:
http://web.utk.edu/~syen/postdoc.html
_______________________________________________
Limdep site list
Limdep at limdep.itls.usyd.edu.au
http://limdep.itls.usyd.edu.au


-- 
Professor William Greene
Department of Economics
Stern School of Business
New York University
44 West 4th St., Rm. 7-78
New York, NY   10012
http://www.stern.nyu.edu/~wgreene
212.998.0876




More information about the Limdep mailing list