A Jonckheere–Terpstra-type test for perfect ranking in balanced ranked set sampling

• DOI: 10.1016/j.jspi.2010.07.005
• Publication Date: 2010-07-12T12:00:00Z
• Authors: Michael Vock; N. Balakrishnan
• Keywords: RSS; Statistic

Abstract Many methods based on ranked set sampling (RSS) assume perfect ranking of the samples. Here, by using the data measured by a balanced RSS scheme, we propose a nonparametric test for the assumption of perfect ranking. The test statistic that we use formally corresponds to the Jonckheere–Terpstra-type test statistic. We show formal relations of the proposed test for perfect ranking to other methods proposed recently in the literature. Through an empirical power study, we demonstrate that the proposed method performs favorably compared to many of its competitors.