A New Class of Distribution-Free Tests for Location Parameters

Abstract

A new class of distribution-free tests for the two-sample location problem is proposed. The tests are based on two-sample U-statistics. This class basically generalizes the tests proposed by Deshpande, J.V.; Kochar, S.C. Some competitors of Wilcoxon–Mann–Whitney test for location alternatives. Journal of Indian Statistical Association 1982, 19, 9–18. The proposed class of tests is also extended to the k (≥ 2)-sample problem for testing homogeneity of location parameters against ordered alternatives. This extension is based on linear combinations of two-sample U-statistics. Pitman asymptotic relative efficiencies (AREs) of the members of the proposed class(es) of tests relative to some of the existing tests are computed for a number of underlying distributions. It is shown that the proposed class of tests performs as good as or better than its competitors in literature.

Keywords:

• Two-sample problem
• k-Sample problem
• U-statistics
• Location parameters
• Pitman asymptotic relative efficiency

Acknowledgments

We are pleased to thank the referee for his useful comments and suggestions. The research is supported in part by the Natural Sciences and Engineering Research Council of Canada, Grant #A4631.

Recommended by P. K. Sen