Sufficient condition for admissibility of the Wilcoxon test in the classical two-sample problem

被引:1
|
作者
Yu, QQ [1 ]
机构
[1] SUNY Binghamton, Dept Math Sci, Binghamton, NY 13902 USA
关键词
continuous distribution functions; nonparametric hypothesis tests; linear rank tests;
D O I
10.1080/02331880310001657778
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
We consider nonparametric two-sample problems of testing the equality of two continuous distribution functions F and G. Whether or not the Wilcoxon test is admissible within the class of all tests, and whether or not the two-sided Wilcoxon test is admissible within the class of all rank tests are two longstanding open questions (Lehmann, 1959; 1986: Ferguson, 1967). In this article, we establish a sufficient condition that the Wilcoxon test is admissible in these two-sample problems. As an application, we show that for some special cases, the Wilcoxon test is admissible within the class of all tests and the two-sided Wilcoxon test is admissible within the class of all rank tests. The author believes that the sufficient condition can be used to solve the longstanding open questions in Lehmann (1959) on a case-by-case basis, but is unable to produce a unified proof for all cases.
引用
收藏
页码:295 / 305
页数:11
相关论文
共 50 条