TY - JOUR
T1 - Testing the hypothesis of a doubly exchangeable covariance matrix
AU - Coelho, Carlos A.
AU - Roy, Anuradha
N1 - info:eu-repo/grantAgreement/FCT/5876/147204/PT#
This research was partially supported by CMA/FCT/UNL, under projects UID/MAT/00297/2013 and UID/MAT/00297/2019. The second author thanks the support for the summer research Grant from the College of Business at the University of Texas at San Antonio.
PY - 2020/1/1
Y1 - 2020/1/1
N2 - In this paper the authors study the problem of testing the hypothesis of a doubly exchangeable covariance matrix for three-level multivariate observations, taken on m variables over u sites and over v time/space points. Through the decomposition of the main hypothesis into a set of three sub-hypotheses, the likelihood ratio test statistic is defined, its exact moments are determined, and its exact distribution is studied. Because this distribution is very much intricate, a very precise near-exact distribution is developed. Numerical studies conducted to evaluate the closeness between this near-exact distribution and the exact distribution show the very good performance of this approximation even for very small sample sizes. A simulation study is also conducted and two real-data examples are presented.
AB - In this paper the authors study the problem of testing the hypothesis of a doubly exchangeable covariance matrix for three-level multivariate observations, taken on m variables over u sites and over v time/space points. Through the decomposition of the main hypothesis into a set of three sub-hypotheses, the likelihood ratio test statistic is defined, its exact moments are determined, and its exact distribution is studied. Because this distribution is very much intricate, a very precise near-exact distribution is developed. Numerical studies conducted to evaluate the closeness between this near-exact distribution and the exact distribution show the very good performance of this approximation even for very small sample sizes. A simulation study is also conducted and two real-data examples are presented.
KW - Characteristic function
KW - Composition of hypotheses
KW - Distribution of likelihood ratio statistics
KW - Mixtures
KW - Near-exact distributions
KW - Product distribution
UR - http://www.scopus.com/inward/record.url?scp=85068840240&partnerID=8YFLogxK
U2 - 10.1007/s00184-019-00724-7
DO - 10.1007/s00184-019-00724-7
M3 - Article
AN - SCOPUS:85068840240
SN - 0026-1335
VL - 83
SP - 45
EP - 68
JO - Metrika
JF - Metrika
IS - 1
ER -