TY - JOUR
T1 - Likelihood ratio tests for covariance matrices of high-dimensional normal distributions
AU - Jiang, Dandan
AU - Jiang, Tiefeng
AU - Yang, Fan
N1 - Copyright:
Copyright 2012 Elsevier B.V., All rights reserved.
PY - 2012/8
Y1 - 2012/8
N2 - For a random sample of size n obtained from a p-variate normal population, the likelihood ratio test (LRT) for the covariance matrix equal to a given matrix is considered. By using the Selberg integral, we prove that the LRT statistic converges to a normal distribution under the assumption p/n→y∈(0, 1]. The result for y=1 is much different from the case for y∈(0, 1). Another test is studied: given two sets of random observations of sample size n 1 and n 2 from two p-variate normal distributions, we study the LRT for testing the two normal distributions having equal covariance matrices. It is shown through a corollary of the Selberg integral that the LRT statistic has an asymptotic normal distribution under the assumption p/n 1→y 1∈(0, 1] and p/n 2→y 2∈(0, 1]. The case for max{y 1, y 2}=1 is much different from the case max{y 1, y 2}<1.
AB - For a random sample of size n obtained from a p-variate normal population, the likelihood ratio test (LRT) for the covariance matrix equal to a given matrix is considered. By using the Selberg integral, we prove that the LRT statistic converges to a normal distribution under the assumption p/n→y∈(0, 1]. The result for y=1 is much different from the case for y∈(0, 1). Another test is studied: given two sets of random observations of sample size n 1 and n 2 from two p-variate normal distributions, we study the LRT for testing the two normal distributions having equal covariance matrices. It is shown through a corollary of the Selberg integral that the LRT statistic has an asymptotic normal distribution under the assumption p/n 1→y 1∈(0, 1] and p/n 2→y 2∈(0, 1]. The case for max{y 1, y 2}=1 is much different from the case max{y 1, y 2}<1.
KW - Gamma function
KW - High-dimensional data
KW - Selberg integral
KW - Testing on covariance matrices
UR - http://www.scopus.com/inward/record.url?scp=84859561923&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84859561923&partnerID=8YFLogxK
U2 - 10.1016/j.jspi.2012.02.057
DO - 10.1016/j.jspi.2012.02.057
M3 - Article
AN - SCOPUS:84859561923
SN - 0378-3758
VL - 142
SP - 2241
EP - 2256
JO - Journal of Statistical Planning and Inference
JF - Journal of Statistical Planning and Inference
IS - 8
ER -