Semiparametric Specification Testing

We propose a specification test of a parametrically specified model against a weakly specified alternative. The latter is estimated using K nonparametric nearest neighbors (K-NN) in the context of an artificial regression. We derived the asymptotic distribution under the null hypothesis and under a series of local alternatives. Monte Carlo simulations suggest that the test is quite powerful although it has a tendency to over-reject under the null hypothesis.

MoreLess

Year of publication:	1990
Authors:	Delgado, Miguel A. ; Stengos, Thanasis
Publisher:	Kingston (Ontario) : Queen's University, Department of Economics
Subject:	K-nearest neighbor regression \| artificial nesting \| nonested hypothesis

More details

Series:	Queen's Economics Department Working Paper ; 778
Type of publication:	Book / Working Paper
Type of publication (narrower categories):	Working Paper
Language:	English
Other identifiers:	hdl:10419/189104 [Handle] RePEC:qed:wpaper:778 [RePEc]
Source:	EconStor

Persistent link: https://www.econbiz.de/10011940442