Return Anomalies on the Nikkei: Are They Statistical Illusions?

18 Pages Posted: 26 May 2003

See all articles by Jonathan A. Batten

Jonathan A. Batten

RMIT University

Craig Ellis

Education Centre Australia

Thomas Fetherston

University of Alabama at Birmingham

Date Written: February 28, 2003

Abstract

This study investigates the sensitivity of the long-term return anomaly observed on the Nikkei stock index to sample and method bias using daily data from the period 3 January 1980 to 31 October 2000. Initially, the CUSUM statistic is employed to identify sub-periods of sign shifts in the mean returns. We find that the null hypothesis of no long-term dependence is accepted for the whole sample and every sub-period using the modified rescaled range test, but not using the classical rescaled adjusted range test. We conclude that researchers may inadvertently introduce sample and method bias into their studies of the time series properties of the Nikkei unless sample period and method are considered.

Keywords: Long-term dependence, Return Anomalies, CUSUM, Rescaled-range statistic, Hurst statistic

JEL Classification: C49, F31, G15

Suggested Citation

Batten, Jonathan A. and Ellis, Craig and Fetherston, Thomas A., Return Anomalies on the Nikkei: Are They Statistical Illusions? (February 28, 2003). Available at SSRN: https://ssrn.com/abstract=396680 or http://dx.doi.org/10.2139/ssrn.396680

Jonathan A. Batten (Contact Author)

RMIT University ( email )

Level 12, 239 Bourke Street
Melbourne, Victoria
Australia

HOME PAGE: http://https://www.rmit.edu.au/contact/staff-contacts/academic-staff/b/batten-professor-jonathan

Craig Ellis

Education Centre Australia ( email )

Sydney
Australia

Thomas A. Fetherston

University of Alabama at Birmingham ( email )

Birmingham, AL 35294
United States
205-934-8860 (Phone)
205-975-6234 (Fax)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
418
Abstract Views
2,191
rank
89,731
PlumX Metrics