Testing the equality of multivariate means when p> n by combining the Hotelling and Simes tests

Tzviel Frostig*, Yoav Benjamini

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

We propose a method of testing a shift between mean vectors of two multivariate Gaussian random variables in a high-dimensional setting incorporating the possible dependency and allowing p> n. This method is a combination of two well-known tests: the Hotelling test and the Simes test. The tests are integrated by sampling several dimensions at each iteration, testing each using the Hotelling test, and combining their results using the Simes test. We prove that this procedure is valid asymptotically. This procedure can be extended to handle non-equal covariance matrices by plugging in the appropriate extension of the Hotelling test. Using a simulation study, we show that the proposed test is advantageous over state-of-the-art tests in many scenarios and robust to violation of the Gaussian assumption.

Original languageEnglish
Pages (from-to)390-415
Number of pages26
JournalTest
Volume31
Issue number2
DOIs
StatePublished - Jun 2022

Keywords

  • Global null
  • Location alternative
  • Permutation testing

Fingerprint

Dive into the research topics of 'Testing the equality of multivariate means when p> n by combining the Hotelling and Simes tests'. Together they form a unique fingerprint.

Cite this