Monotone false discovery rate
Methodology
2013-12-16 v3
Abstract
This paper proposes a procedure to obtain monotone estimates of both the local and the tail false discovery rates that arise in large-scale multiple testing. The proposed monotonization is asymptotically optimal for controlling the false discovery rate and also has many attractive finite-sample properties.
Cite
@article{arxiv.1305.6340,
title = {Monotone false discovery rate},
author = {Joong-Ho Won and Johan Lim and Donghyeon Yu and Byung Soo Kim and Kyunga Kim},
journal= {arXiv preprint arXiv:1305.6340},
year = {2013}
}