Asymptotically optimal test for dependent multiple testing set up
Statistics Theory
2020-01-09 v1 Methodology
Statistics Theory
Abstract
In this paper we explore the behaviour of dependent test statistics for testing of multiple hypothesis . To keep simplicity, we have considered a mixture normal model with equicorrelated correlation set up. With a simple linear transformation,the test statistics were decomposed into independent components, which, when conditioned appropriately generated independent variables. These were used to construct conditional tests , which were shown to be asymptotically optimal with power as large as that obtained using N.P.Lemma. We have pursued extensive simulation to support the claim.
Cite
@article{arxiv.2001.02229,
title = {Asymptotically optimal test for dependent multiple testing set up},
author = {Rahul Roy and Subir Kumar Bhandari},
journal= {arXiv preprint arXiv:2001.02229},
year = {2020}
}