Combining Two Nonparametric Tests Of Location

Abstract

A distribution-free test is proposed whose power is similar to that of the Wilcoxon Rank-Sum or Terry-Hoeffding
Normal Scores tests depending on which of these two tests is more powerful in a given data analysis situation, regardless
of the population. This new statistic is distribution-free, and adds no new assumptions to those associated with the
constituent tests. A table of critical values for the new statistic is given and some of its Type I error and power properties
are examined.