A0703
Title: Statistical inference based on weighted divergence measures
Authors: Thomas Gkelsinis - University of Rouen - Normandy (France)
Alexandros Karagrigoriou - University of The Aegean (Greece)
Vlad Stefan Barbu - University of Rouen-Normandy (France) [presenting]
Abstract: The focus is on a class of hypotheses tests for goodness of fit and homogeneity between two samples. This type of test is constructed based on a particular type of discrepancy measure called weighted divergences. These measures allow us to focus on specific subsets of the support without, at the same time, losing the information of the others. With this method, we achieve a significantly more sensitive test than the classical ones, with comparable error rates. The appropriate asymptotic theory is presented according to Monte Carlo simulations for assessing the performance of the proposed test statistics.
