|
Activity Number:
|
587
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Thursday, August 6, 2009 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Business and Economic Statistics Section
|
| Abstract - #303886 |
|
Title:
|
Copula-Based Tests of Independence Among Continuous Random Vectors
|
|
Author(s):
|
Ivan Kojadinovic*+
|
|
Companies:
|
The University of Auckland
|
|
Address:
|
Department of Statistics, Private Bag 92019, Auckland, 1142, New Zealand
|
|
Keywords:
|
Empirical process ; Mobius decomposition ; Cramer-von Mises statistic ; Bootstrap ; Permutation
|
|
Abstract:
|
Tests of independence among p continuous random vectors are presented. They are based on a decomposition of the independence empirical copula process into a finite number of asymptotically independent sub-processes in the spirit of that studied by Deheuvels, and Genest and Remillard. The asymptotic behavior of the resulting collection of Cramer-von Mises statistics is derived. As they are not distribution-free, one way of carrying out the resulting tests of independence involves using the bootstrap or the permutation methodology. The former is shown to behave consistently, while the latter is employed in practice. The finite-sample behavior of the proposed tests is illustrated by means of extensive simulations.
|
