A1466
Title: Tests of independence and randomness for arbitrary data using copula-based covariances
Authors: Bouchra Nasri - University of Montreal (Canada) [presenting]
Bruno Remillard - HEC Montreal (Canada)
Abstract: Tests of independence for data with arbitrary distributions in both non-serial and serial settings are discussed. These tests are constructed using copula-based covariances and their multivariate extensions via Mobius transforms. Their asymptotic properties are examined, results from numerical experiments are presented, and the methodology is illustrated with a data-driven example.
