Permutation test for the multivariate coefficient of variation in factorial designs

Abstract: New inference methods for the multivariate coefficient of variation and its reciprocal, the standardized mean, are presented. While there are various testing procedures for both parameters in the univariate case, it is less known how to do inference in the multivariate setting appropriately. There are some existing procedures but they rely on restrictive assumptions on the underlying distributions. We tackle this problem by applying Wald-type statistics in the context of general, potentially heteroscedastic factorial designs. In addition to the $k$-sample case, higher-way layouts can be incorporated into this framework allowing the discussion of main and interaction effects. The resulting procedures are shown to be asymptotically valid under the null hypothesis and consistent under general alternatives. To improve the finite sample performance, we suggest permutation versions of the tests and shown that the tests' asymptotic properties can be transferred to them. An exhaustive simulation study compares the new tests, their permutation counterparts and existing methods. To further analyse the differences between the tests, we conduct two illustrative real data examples.