An extension of the ordinary permutation solution of the two-sample location problem

Abstract

In this paper, a permutation method for comparing locations of two populations has been proposed. Due to the way it has been devised, this test allows a deeper inference on testing the studied system of hypotheses than that allowed by the order methods using exactly the same sample data. Furthermore, simulation results show that, in the considered contexts, it performs practically as well as the optimal parametric solution in terms of power and it maintains its size close to the nominal significance level.