The Annals of Mathematical Statistics

On the Efficiency of a Competitor of the Two-Sample Kolmogorov-Smirnov and Kuiper Tests

Ramon C. Littell

Full-text: Open access

Abstract

In a paper by Abrahamson [1], it is shown that the Kuiper test generally performs better than the Kolmogorov-Smirnov (K-S) test according to exact Bahadur relative efficiency. The present note concerns the Bahadur efficiency of a related test statistic $U_n$ whose exact null probability distribution is available in the two-sample case with equal sample sizes. It is shown that $U_n$ is often more efficient than the K-S test and may even be as efficient as the Kuiper test.

Article information

Source
Ann. Math. Statist., Volume 43, Number 6 (1972), 1991-1992.

Dates
First available in Project Euclid: 27 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aoms/1177690871

Digital Object Identifier
doi:10.1214/aoms/1177690871

Mathematical Reviews number (MathSciNet)
MR359165

Zentralblatt MATH identifier
0248.62025

JSTOR
links.jstor.org

Citation

Littell, Ramon C. On the Efficiency of a Competitor of the Two-Sample Kolmogorov-Smirnov and Kuiper Tests. Ann. Math. Statist. 43 (1972), no. 6, 1991--1992. doi:10.1214/aoms/1177690871. https://projecteuclid.org/euclid.aoms/1177690871


Export citation