Ordered inference, rank statistics and combining p-values: A new perspective

Ori Davidov

doi:10.1016/j.stamet.2011.10.003

Ordered inference, rank statistics and combining p-values: A new perspective

Ori Davidov

Department of Statistics

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

Abstract

A family of simple two sample rank tests for testing for stochastic order is introduced. The proposed tests are motivated by the stochastic ordering of the ranks and methods for combining p-values which capitalize on this ordering. We show that the new tests coincide with some well known rank tests. Their large sample distributions are derived under various assumptions on the sample sizes. Some optimality properties are discussed. Simulations show that the new tests perform well, often better than specialized tests designed for testing for order among two populations.

Original language	English
Pages (from-to)	456-465
Number of pages	10
Journal	Statistical Methodology
Volume	9
Issue number	3
DOIs	https://doi.org/10.1016/j.stamet.2011.10.003
State	Published - May 2012

Bibliographical note

Funding Information:
This research was partially supported by the Israeli Science Foundation Grant No. 875/09 . We would like to thank Shyamal Peddada (NIEHS) for several useful comments that improved the presentation.

Keywords

Combining p-values
Rank tests
Stochastic order relations

ASJC Scopus subject areas

Statistics and Probability

Access to Document

10.1016/j.stamet.2011.10.003

Cite this

@article{cc37da55560d4b98ae4d9b1cec6af816,

title = "Ordered inference, rank statistics and combining p-values: A new perspective",

abstract = "A family of simple two sample rank tests for testing for stochastic order is introduced. The proposed tests are motivated by the stochastic ordering of the ranks and methods for combining p-values which capitalize on this ordering. We show that the new tests coincide with some well known rank tests. Their large sample distributions are derived under various assumptions on the sample sizes. Some optimality properties are discussed. Simulations show that the new tests perform well, often better than specialized tests designed for testing for order among two populations.",

keywords = "Combining p-values, Rank tests, Stochastic order relations",

author = "Ori Davidov",

note = "Funding Information: This research was partially supported by the Israeli Science Foundation Grant No. 875/09 . We would like to thank Shyamal Peddada (NIEHS) for several useful comments that improved the presentation. ",

year = "2012",

month = may,

doi = "10.1016/j.stamet.2011.10.003",

language = "English",

volume = "9",

pages = "456--465",

journal = "Statistical Methodology",

issn = "1572-3127",

publisher = "Elsevier",

number = "3",

}

TY - JOUR

T1 - Ordered inference, rank statistics and combining p-values

T2 - A new perspective

AU - Davidov, Ori

N1 - Funding Information: This research was partially supported by the Israeli Science Foundation Grant No. 875/09 . We would like to thank Shyamal Peddada (NIEHS) for several useful comments that improved the presentation.

PY - 2012/5

Y1 - 2012/5

N2 - A family of simple two sample rank tests for testing for stochastic order is introduced. The proposed tests are motivated by the stochastic ordering of the ranks and methods for combining p-values which capitalize on this ordering. We show that the new tests coincide with some well known rank tests. Their large sample distributions are derived under various assumptions on the sample sizes. Some optimality properties are discussed. Simulations show that the new tests perform well, often better than specialized tests designed for testing for order among two populations.

AB - A family of simple two sample rank tests for testing for stochastic order is introduced. The proposed tests are motivated by the stochastic ordering of the ranks and methods for combining p-values which capitalize on this ordering. We show that the new tests coincide with some well known rank tests. Their large sample distributions are derived under various assumptions on the sample sizes. Some optimality properties are discussed. Simulations show that the new tests perform well, often better than specialized tests designed for testing for order among two populations.

KW - Combining p-values

KW - Rank tests

KW - Stochastic order relations

UR - http://www.scopus.com/inward/record.url?scp=84855206593&partnerID=8YFLogxK

U2 - 10.1016/j.stamet.2011.10.003

DO - 10.1016/j.stamet.2011.10.003

M3 - Article

AN - SCOPUS:84855206593

SN - 1572-3127

VL - 9

SP - 456

EP - 465

JO - Statistical Methodology

JF - Statistical Methodology

IS - 3

ER -

Ordered inference, rank statistics and combining p-values: A new perspective

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this