[Limdep Nlogit List] Ordered probit/logit on percentage brackets

[Alessandro Corsi]

Hello everybody

I have a sample of firms that export part of their production. The share 
of export over their production is reported in percentage brackets 
(e.g., less than 15%; 15-50%, etc.). The specific bracket of each firm 
is my dependent variable in a model with several explanatory variables: 
the dependent variable is clearly ordered and not continuous, but it is 
constrained between 0 and 1 (or 0%-100%). I ran an ordered probit with 
Limdep, and received no warning, but I am uncertain about my results.

My question is: Is it appropriate to use an ordered probit? Is the 0 to 
1 range of the dependent variable a problem? and, if so, are there 
alternative methods to handle the problem, and how do they work in Limdep?

Thanks

Alessandro

______________________

Alessandro Corsi
Dept of Economics and Statistics "Cognetti de Martiis"
University of Torino, Italy

-- 
Questa email è stata esaminata alla ricerca di virus dal software antivirus Avast.
https://protect-au.mimecast.com/s/-d1lCoV1kpfDODoE1f1cUZ3?domain=avast.com