Monotonicity properties of multiple endpoint testing procedures

Arthur Cohen; H. B. Sackrowitz

doi:10.1016/j.jspi.2003.10.008

Monotonicity properties of multiple endpoint testing procedures

Arthur Cohen, H. B. Sackrowitz

School of Arts and Sciences, Statistics

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

Multiple endpoint testing procedures concerned with k means are viewed as decision rules for a 2^k finite action problem. A loss function which is the sum of losses for each endpoint problem is assumed. Procedures including the single-step, step-down, and step-up are considered. Two types of monotonicity of procedures are defined. In addition, a compelling property, namely monotonicity of the risk function is also studied for each procedure. Some further results relating monotone procedures to a complete class, to Bayes procedures and likelihood procedures are presented.

Original language	English (US)
Pages (from-to)	17-30
Number of pages	14
Journal	Journal of Statistical Planning and Inference
Volume	125
Issue number	1-2
DOIs	https://doi.org/10.1016/j.jspi.2003.10.008
State	Published - Oct 2004

All Science Journal Classification (ASJC) codes

Statistics and Probability
Statistics, Probability and Uncertainty
Applied Mathematics

Keywords

Familywise error rate
Finite action problems
Global problem
Intraclass correlation
Single-step
Step-down
Step-up

Access to Document

10.1016/j.jspi.2003.10.008

Cite this

@article{be7ac12fecea4e878a6d622b72f5bd2f,

title = "Monotonicity properties of multiple endpoint testing procedures",

abstract = "Multiple endpoint testing procedures concerned with k means are viewed as decision rules for a 2k finite action problem. A loss function which is the sum of losses for each endpoint problem is assumed. Procedures including the single-step, step-down, and step-up are considered. Two types of monotonicity of procedures are defined. In addition, a compelling property, namely monotonicity of the risk function is also studied for each procedure. Some further results relating monotone procedures to a complete class, to Bayes procedures and likelihood procedures are presented.",

keywords = "Familywise error rate, Finite action problems, Global problem, Intraclass correlation, Single-step, Step-down, Step-up",

author = "Arthur Cohen and Sackrowitz, {H. B.}",

note = "Funding Information: Research supported by National Security Agency Grant MDA 904-02-1-0039. ",

year = "2004",

month = oct,

doi = "10.1016/j.jspi.2003.10.008",

language = "English (US)",

volume = "125",

pages = "17--30",

journal = "Journal of Statistical Planning and Inference",

issn = "0378-3758",

publisher = "Elsevier",

number = "1-2",

}

TY - JOUR

T1 - Monotonicity properties of multiple endpoint testing procedures

AU - Cohen, Arthur

AU - Sackrowitz, H. B.

N1 - Funding Information: Research supported by National Security Agency Grant MDA 904-02-1-0039.

PY - 2004/10

Y1 - 2004/10

N2 - Multiple endpoint testing procedures concerned with k means are viewed as decision rules for a 2k finite action problem. A loss function which is the sum of losses for each endpoint problem is assumed. Procedures including the single-step, step-down, and step-up are considered. Two types of monotonicity of procedures are defined. In addition, a compelling property, namely monotonicity of the risk function is also studied for each procedure. Some further results relating monotone procedures to a complete class, to Bayes procedures and likelihood procedures are presented.

AB - Multiple endpoint testing procedures concerned with k means are viewed as decision rules for a 2k finite action problem. A loss function which is the sum of losses for each endpoint problem is assumed. Procedures including the single-step, step-down, and step-up are considered. Two types of monotonicity of procedures are defined. In addition, a compelling property, namely monotonicity of the risk function is also studied for each procedure. Some further results relating monotone procedures to a complete class, to Bayes procedures and likelihood procedures are presented.

KW - Familywise error rate

KW - Finite action problems

KW - Global problem

KW - Intraclass correlation

KW - Single-step

KW - Step-down

KW - Step-up

UR - http://www.scopus.com/inward/record.url?scp=4043176337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4043176337&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2003.10.008

DO - 10.1016/j.jspi.2003.10.008

M3 - Article

AN - SCOPUS:4043176337

SN - 0378-3758

VL - 125

SP - 17

EP - 30

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

IS - 1-2

ER -

Monotonicity properties of multiple endpoint testing procedures

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this