Title
Miscellanea: Testing For Complete Independence In High Dimensions
Keywords
High-dimensional data; Independence of random variables
Abstract
A simple statistic is proposed for testing the complete independence of random variables having a multivariate normal distribution. The asymptotic null distribution of this statistic, as both the sample size 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 size and, in particular, even when the number of variables exceeds the sample size. The finite sample size performance of the normal approximation is evaluated in a simulation study and the results are compared to those of the likelihood ratio test. © 2005 Biometrika Trust.
Publication Date
12-1-2005
Publication Title
Biometrika
Volume
92
Issue
4
Number of Pages
951-956
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1093/biomet/92.4.951
Copyright Status
Unknown
Socpus ID
27944479075 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/27944479075
STARS Citation
Schott, James R., "Miscellanea: Testing For Complete Independence In High Dimensions" (2005). Scopus Export 2000s. 3500.
https://stars.library.ucf.edu/scopus2000/3500