English

$k$-Sample problem based on generalized maximum mean discrepancy

Statistics Theory 2018-11-26 v1 Statistics Theory

Abstract

In this paper we deal with the problem of testing for the quality of kk probability distributions. We introduce a generalization of the maximum mean discrepancy that permits to characterize the null hypothesis. Then, an estimator of it is proposed as test statistic, and its asymptotic distribution under the null hypothesis is derived. Simulations show that the introduced procedure outperforms classical ones.

Keywords

Cite

@article{arxiv.1811.09103,
  title  = {$k$-Sample problem based on generalized maximum mean discrepancy},
  author = {Armando Sosthene Kali Balogoun and Guy Martial Nkiet and Carlos Ogouyandjou},
  journal= {arXiv preprint arXiv:1811.09103},
  year   = {2018}
}

Comments

20 pages, 4 figures