A rank test for bivariate location and scale problem for elliptically symmetric populations^∗

^∗Research supported in part by NSERC (Canada) and the FRSQ (Quebec).

Abstract

A nonparametric rank test for the two-sample location and scale bivariate problem is proposed. The asymptotic distribution of the statistic of the test is derived under the null hypothesis and under a class of contiguous alternatives. The asymptotic relative efficiency is given and a simulation study gives the performance of the test and some competitors.

Keywords:

• rank test
• elliptic distribution
• hivariate location problem
• bivariate scale problem
• Behrens-Fisher problem
• contiguity
• asymptotic distribution

^∗Research supported in part by NSERC (Canada) and the FRSQ (Quebec).

^∗Research supported in part by NSERC (Canada) and the FRSQ (Quebec).

Notes

^∗Research supported in part by NSERC (Canada) and the FRSQ (Quebec).

Additional information

Notes on contributors

M. Mountassir