k-Sample problem based on generalized maximum mean discrepancy

2018/11/22 by Balogoun, Armando Sosthene Kali, Nkiet, Guy Martial, Ogouyandjou, Carlos
#62G10 #62G20 #FOS: Mathematics #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.1811.09103

Abstract

In this paper we deal with the problem of testing for the quality of k 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.

Related

• Maximum Mean Discrepancy with Unequal Sample Sizes via Generalized U-Statistics
• Testing for homogeneity of several functional variables via multiple maximum variance discrepancy
• Two-sample test based on maximum variance discrepancy
• Asymptotic normality of a generalized maximum mean discrepancy estimator
• A Martingale Kernel Two-Sample Test