Publication: Non-parametric specification testing of non-nested econometric models
Loading...
Identifiers
Publication date
1994-12
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
We consider the non-nested testing prqblem of non-parametric regressions. We show that, when the regression functions are unknown under both the null and the alternative hypotheses, an extension of the J-test procedure of Davidson and Mackinnon (1981) will lead to a test statistic with well defined asymptotic properties. The derivation of the test statistic involves double kernel estimation. Monte Carlo simulations suggest that the test has good size and power characteristics.
Description
Keywords
Non-parametric test, Non-nested models, Double kernel estimation