Multiple Comparisons with Control Under Stochastic Ordering: Controlling FDR

Jianwei Gou and Jinde Wang

Communications in Statistics - Theory and Methods, 2015, vol. 44, issue 21, 4507-4520

Abstract: Multiple comparisons of the effects of several treatments with a control (MCC) has been a central problem in medicine and other areas. Nearly all of existing papers are devoted to comparing means of the effects. To study medical problems more deeply, one needs more information than mean relationship from the given data. It can be expected to get more useful and deeper conclusion by comparing the probability distributions, i.e., by comparison under stochastic orders. This paper presents a likelihood ratio testing procedure to compare effects under stochastic order for MCC problems, controlling the false discovery rate (FDR). Setting a test controlling FDR under stochastic order faces several non trivial problems. These problems are analyzed and solved in this paper. To facilitate the test more easily, the asymptotic p values for the test are used and their distributions are derived. It is shown that controllability of FDR for this comparison procedure can be guaranteed. A real data example is used to illustrate how to apply this testing procedure and what the test can tell. Simulation results show that this testing procedure works quite well, better than some other tests.

Date: 2015
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/03610926.2013.810271 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:lstaxx:v:44:y:2015:i:21:p:4507-4520

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/lsta20

DOI: 10.1080/03610926.2013.810271

Access Statistics for this article

Communications in Statistics - Theory and Methods is currently edited by Debbie Iscoe

More articles in Communications in Statistics - Theory and Methods from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().