Bernoulli

  • Bernoulli
  • Volume 9, Number 2 (2003), 267-290.

Empirical likelihood based hypothesis testing

John H.J. Einmahl and Ian W. Mckeague

Full-text: Open access

Abstract

Omnibus tests for various nonparametric hypotheses are developed using the empirical likelihood method. These include tests for symmetry about zero, changes in distribution, independence and exponentiality. The approach is to localize the empirical likelihood using a suitable `time' variable implicit in the null hypothesis and then form an integral of the log-likelihood ratio statistic. The asymptotic null distributions of these statistics are established. In simulation studies, the proposed statistics are found to have greater power than corresponding Cram\'er--von Mises type statistics.

Article information

Source
Bernoulli, Volume 9, Number 2 (2003), 267-290.

Dates
First available in Project Euclid: 6 November 2003

Permanent link to this document
https://projecteuclid.org/euclid.bj/1068128978

Digital Object Identifier
doi:10.3150/bj/1068128978

Mathematical Reviews number (MathSciNet)
MR1997030

Zentralblatt MATH identifier
1015.62048

Keywords
change point distribution-free exponentiality independence nonparametric likelihood ratio symmetry two-sample problem

Citation

Einmahl, John H.J.; Mckeague, Ian W. Empirical likelihood based hypothesis testing. Bernoulli 9 (2003), no. 2, 267--290. doi:10.3150/bj/1068128978. https://projecteuclid.org/euclid.bj/1068128978


Export citation