Asymptotic distribution‐free tests related to maximum mean discrepancy

Kai Xu

Scandinavian Journal of Statistics, 2025, vol. 52, issue 4, 2110-2127

Abstract: The topic of maximum mean discrepancy has been prominent in statistical analyses of multivariate two‐sample goodness of fit. Despite its usefulness, one major bottleneck is the testing process: Because the null distribution of maximum mean discrepancy depends on the underlying distribution, it typically requires a permutation test to estimate the null and compute the p$$ p $$‐value, which is very costly for a large amount of data. To overcome the difficulty, in this article, we propose combined probability tests based on the equality of the means of a characteristic kernel, which arises in maximum mean discrepancy analysis of multivariate data. The combined probability tests are shown to be asymptotically distribution‐free and therefore have well‐known critical values. We further show that the proposed tests are consistent against all fixed alternatives under the existence of the second moment of the characteristic kernel. A local power analysis provides strong support for the new approach by establishing the nontrivial power of our tests over square root‐(m+n)−1$$ {\left(m+n\right)}^{-1} $$ neighborhoods. We illustrate the advantages of the proposed method via simulation studies and a gene expression dataset analysis.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1111/sjos.70019

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bla:scjsta:v:52:y:2025:i:4:p:2110-2127

Ordering information: This journal article can be ordered from
http://www.blackwell ... bs.asp?ref=0303-6898

Access Statistics for this article

Scandinavian Journal of Statistics is currently edited by ÿrnulf Borgan and Bo Lindqvist

More articles in Scandinavian Journal of Statistics from Danish Society for Theoretical Statistics, Finnish Statistical Society, Norwegian Statistical Association, Swedish Statistical Association
Bibliographic data for series maintained by Wiley Content Delivery ().