A test for the equality of covariance matrices when the dimension is large relative to the sample sizes

    Authors

    J. R. Schott

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    Comput. Stat. Data Anal.

    Keywords

    equal covariance matrices; high-dimensional data; singular sample; covariance matrix; GENE-EXPRESSION; Computer Science, Interdisciplinary Applications; Statistics &; Probability

    Abstract

    A simple statistic is proposed for testing the equality of the covariance matrices of several multivariate normal populations. The asymptotic null distribution of this statistic, as both the sample sizes and the number of variables go to infinity, is shown to be normal. Consequently, this test can be used when the number of variables is not small relative to the sample sizes and, in particular, even when the number of variables exceeds the sample sizes. The finite sample size performance of the normal approximation for this method is evaluated in a simulation study. (c) 2007 Elsevier B.V. All rights reserved.

    Journal Title

    Computational Statistics & Data Analysis

    Volume

    51

    Issue/Number

    12

    Publication Date

    1-1-2007

    Document Type

    Article

    Language

    English

    First Page

    6535

    Last Page

    6542

    WOS Identifier

    WOS:000249316000083

    ISSN

    0167-9473

    Share

    COinS