Empirical likelihood specification testing in linear regression models

This paper analyses the higher order asymptotic behaviour of a profiled empirical likelihood ratio which can be used as a specification test in linear regression models. Despite the presence of nuisance parameters, a simple Bartlett correction factor is obtained and used to improve to third order the accuracy of commonly used tests such as the inclusion of irrelevant variables without any distributional assumptions about the error process.

MoreLess

Authors:	Bravo, Francesco
Institutions:	Department of Economics and Related Studies, University of York

More details

Extent:	application/pdf
Series:	Discussion Papers.
Type of publication:	Book / Working Paper
Language:	English
Classification:	C12 - Hypothesis Testing ; C14 - Semiparametric and Nonparametric Methods
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10005328570