English

Multivariate Mean Comparison under Differential Privacy

Methodology 2021-10-18 v1 Cryptography and Security Statistics Theory Statistics Theory

Abstract

The comparison of multivariate population means is a central task of statistical inference. While statistical theory provides a variety of analysis tools, they usually do not protect individuals' privacy. This knowledge can create incentives for participants in a study to conceal their true data (especially for outliers), which might result in a distorted analysis. In this paper we address this problem by developing a hypothesis test for multivariate mean comparisons that guarantees differential privacy to users. The test statistic is based on the popular Hotelling's t2t^2-statistic, which has a natural interpretation in terms of the Mahalanobis distance. In order to control the type-1-error, we present a bootstrap algorithm under differential privacy that provably yields a reliable test decision. In an empirical study we demonstrate the applicability of this approach.

Keywords

Cite

@article{arxiv.2110.07996,
  title  = {Multivariate Mean Comparison under Differential Privacy},
  author = {Martin Dunsche and Tim Kutta and Holger Dette},
  journal= {arXiv preprint arXiv:2110.07996},
  year   = {2021}
}
R2 v1 2026-06-24T06:54:58.660Z