Testing of (non-nested) choice models via accuracy of prediction: A non-parametric approach

Testing of (non-nested) choice models via accuracy of prediction: A non-parametric approach

0.00 Avg rating0 Votes
Article ID: iaor20013112
Country: Germany
Volume: 8
Issue: 3
Start Page Number: 259
End Page Number: 264
Publication Date: Jun 2000
Journal: Central European Journal of Operations Research
Authors:
Abstract:

In this paper a McNemar-type test is proposed as a general specification test for binary and multinomial choice models. The test has several advantages including: 1) well-known small-sample properties; 2) an asymptotic distribution that works very well even for small samples; 3) a distribution-free nature; and 4) applicability to non-nested models.

Reviews

Required fields are marked *. Your email address will not be published.