Two non parametric methods for change-point detection in distribution. Issue 6 (19th March 2017)

• Record Type: Journal Article
• Authors: Zhou, Yan; Fu, Liya; Zhang, Baoxue
• Is Part Of: Communications in statistics. Volume 46:Issue 6(2017)
• Page Start: 2801
• Page End: 2815
• Publication Date: 2017-03-19
• Subjects: Change-point -- Cusums -- Empirical likelihood -- Likelihood ratio test -- Robust; 62G10; Mathematical statistics -- Periodicals; Mathematics; Statistics; 519.2
• DOI: 10.1080/03610926.2015.1048891
• Languages: English
• ISSNs: 0361-0926

Abstract

ABSTRACT: The change-point detection problem is determining whether a change has taken place. Two non parametric methods based on empirical likelihood and the likelihood ratio are proposed for detecting a change-point problem in distributions for independent observations. Numerical studies are carried out to evaluate the performance of the proposed methods. The simulation results demonstrate that the proposed methods are robust, that is, they perform well regardless of whether the observations are from the same distribution family.