A two sample test in high dimensional data

Muni S. Srivastava, Shota Katayama, Yutaka Kano

Research output: Contribution to journalArticle

49 Citations (Scopus)

Abstract

In this paper we propose a test for testing the equality of the mean vectors of two groups with unequal covariance matrices based on N1 and N2 independently distributed p-dimensional observation vectors. It will be assumed that N1 observation vectors from the first group are normally distributed with mean vector μ1 and covariance matrix Σ1. Similarly, the N2 observation vectors from the second group are normally distributed with mean vectorμ2 and covariance matrixΣ2.Wepropose a test for testing the hypothesis that μ1 = μ2. This test is invariant under the group of p×p nonsingular diagonal matrices. The asymptotic distribution is obtained as (N1, N2, p) → ∞and N1/(N1 + N2) → k ∈ (0, 1) but N1/p and N2/p may go to zero or infinity. It is compared with a recently proposed noninvariant test. It is shown that the proposed test performs the best.

Original languageEnglish
Pages (from-to)349-358
Number of pages10
JournalJournal of Multivariate Analysis
Volume114
Issue number1
DOIs
Publication statusPublished - 2013 Jan 1
Externally publishedYes

Fingerprint

Two-sample Test
High-dimensional Data
Covariance matrix
Testing
Nonsingular or invertible matrix
Diagonal matrix
Unequal
Asymptotic distribution
Equality
Infinity
Invariant
Zero
Observation

Keywords

  • Asymptotic theory
  • Behrens-Fisher problem
  • High-dimensional data
  • Hypothesis testing

ASJC Scopus subject areas

  • Statistics and Probability
  • Numerical Analysis
  • Statistics, Probability and Uncertainty

Cite this

A two sample test in high dimensional data. / Srivastava, Muni S.; Katayama, Shota; Kano, Yutaka.

In: Journal of Multivariate Analysis, Vol. 114, No. 1, 01.01.2013, p. 349-358.

Research output: Contribution to journalArticle

Srivastava, Muni S. ; Katayama, Shota ; Kano, Yutaka. / A two sample test in high dimensional data. In: Journal of Multivariate Analysis. 2013 ; Vol. 114, No. 1. pp. 349-358.
@article{4b60d500be9642669fe633c1866242e7,
title = "A two sample test in high dimensional data",
abstract = "In this paper we propose a test for testing the equality of the mean vectors of two groups with unequal covariance matrices based on N1 and N2 independently distributed p-dimensional observation vectors. It will be assumed that N1 observation vectors from the first group are normally distributed with mean vector μ1 and covariance matrix Σ1. Similarly, the N2 observation vectors from the second group are normally distributed with mean vectorμ2 and covariance matrixΣ2.Wepropose a test for testing the hypothesis that μ1 = μ2. This test is invariant under the group of p×p nonsingular diagonal matrices. The asymptotic distribution is obtained as (N1, N2, p) → ∞and N1/(N1 + N2) → k ∈ (0, 1) but N1/p and N2/p may go to zero or infinity. It is compared with a recently proposed noninvariant test. It is shown that the proposed test performs the best.",
keywords = "Asymptotic theory, Behrens-Fisher problem, High-dimensional data, Hypothesis testing",
author = "Srivastava, {Muni S.} and Shota Katayama and Yutaka Kano",
year = "2013",
month = "1",
day = "1",
doi = "10.1016/j.jmva.2012.08.014",
language = "English",
volume = "114",
pages = "349--358",
journal = "Journal of Multivariate Analysis",
issn = "0047-259X",
publisher = "Academic Press Inc.",
number = "1",

}

TY - JOUR

T1 - A two sample test in high dimensional data

AU - Srivastava, Muni S.

AU - Katayama, Shota

AU - Kano, Yutaka

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In this paper we propose a test for testing the equality of the mean vectors of two groups with unequal covariance matrices based on N1 and N2 independently distributed p-dimensional observation vectors. It will be assumed that N1 observation vectors from the first group are normally distributed with mean vector μ1 and covariance matrix Σ1. Similarly, the N2 observation vectors from the second group are normally distributed with mean vectorμ2 and covariance matrixΣ2.Wepropose a test for testing the hypothesis that μ1 = μ2. This test is invariant under the group of p×p nonsingular diagonal matrices. The asymptotic distribution is obtained as (N1, N2, p) → ∞and N1/(N1 + N2) → k ∈ (0, 1) but N1/p and N2/p may go to zero or infinity. It is compared with a recently proposed noninvariant test. It is shown that the proposed test performs the best.

AB - In this paper we propose a test for testing the equality of the mean vectors of two groups with unequal covariance matrices based on N1 and N2 independently distributed p-dimensional observation vectors. It will be assumed that N1 observation vectors from the first group are normally distributed with mean vector μ1 and covariance matrix Σ1. Similarly, the N2 observation vectors from the second group are normally distributed with mean vectorμ2 and covariance matrixΣ2.Wepropose a test for testing the hypothesis that μ1 = μ2. This test is invariant under the group of p×p nonsingular diagonal matrices. The asymptotic distribution is obtained as (N1, N2, p) → ∞and N1/(N1 + N2) → k ∈ (0, 1) but N1/p and N2/p may go to zero or infinity. It is compared with a recently proposed noninvariant test. It is shown that the proposed test performs the best.

KW - Asymptotic theory

KW - Behrens-Fisher problem

KW - High-dimensional data

KW - Hypothesis testing

UR - http://www.scopus.com/inward/record.url?scp=84867812899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867812899&partnerID=8YFLogxK

U2 - 10.1016/j.jmva.2012.08.014

DO - 10.1016/j.jmva.2012.08.014

M3 - Article

AN - SCOPUS:84867812899

VL - 114

SP - 349

EP - 358

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

IS - 1

ER -