[Limdep Nlogit List] Simultaneous equations with one ordered probit

[William Greene]

Marc. You cannot use 3sls with an ordered probit model. The dependent
variable is just a label for an outcome, not a quantitative measure.
Also, chances are, you are using the textbook benchmarks for indentification
of your model, which are also wrong because you have a discrete dependent
variable.
There is a recent paper in JAE by Rice, Contoyannis and Jones that deals
with an endogenous ordered outcome variable that you might find useful.
/Bill Greene

----- Original Message -----
From: "Marc Goergen" <m.goergen at sheffield.ac.uk>
To: limdep at limdep.itls.usyd.edu.au
Sent: Friday, June 13, 2008 4:25:50 AM (GMT-0500) America/Bogota
Subject: [Limdep Nlogit List] Simultaneous equations with one ordered probit

Dear all

 

I would appreciate your help with the following. I would like to estimate a
system of three equations using 3SLS. Two of the equations are linear
regressions. The third regression is an ordered probit/logit. Is this
something that can be done with Limdep?

 

Best wishes,

 

Marc Goergen

 

 

_______________________________________________
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