A trinomial test for paired data when there are many ties

Guorui Bian; Michael McAleer; Wing-Keung Wong

doi:10.1016/j.matcom.2010.11.002

A trinomial test for paired data when there are many ties

Guorui Bian, Michael McAleer, Wing-Keung Wong^*

^*Corresponding author for this work

Research output: Contribution to journal › Journal article › peer-review

19 Citations (Scopus)

34 Downloads (Pure)

Abstract

This paper develops a new test, the trinomial test, for pairwise ordinal data samples to improve the power of the sign test by modifying its treatment of zero differences between observations, thereby increasing the use of sample information. Simulations demonstrate the power superiority of the proposed trinomial test statistic over the sign test in small samples in the presence of tie observations. We also show that the proposed trinomial test has substantially higher power than the sign test in large samples and also in the presence of tie observations, as the sign test ignores information from observations resulting in ties.

Original language	English
Pages (from-to)	1153-1160
Number of pages	8
Journal	Mathematics and Computers in Simulation
Volume	81
Issue number	6
Early online date	7 Dec 2010
DOIs	https://doi.org/10.1016/j.matcom.2010.11.002
Publication status	Published - Feb 2011

Scopus Subject Areas

Theoretical Computer Science
General Computer Science
Numerical Analysis
Modelling and Simulation
Applied Mathematics

User-Defined Keywords

Non-parametric test
Sign test
Test statistics
Ties
Trinomial test

Access to Document

10.1016/j.matcom.2010.11.002

Full TextAccepted author manuscript, 143 KB

Cite this

@article{7234304390ea4af1b2b1fa755878fd78,

title = "A trinomial test for paired data when there are many ties",

abstract = "This paper develops a new test, the trinomial test, for pairwise ordinal data samples to improve the power of the sign test by modifying its treatment of zero differences between observations, thereby increasing the use of sample information. Simulations demonstrate the power superiority of the proposed trinomial test statistic over the sign test in small samples in the presence of tie observations. We also show that the proposed trinomial test has substantially higher power than the sign test in large samples and also in the presence of tie observations, as the sign test ignores information from observations resulting in ties.",

keywords = "Non-parametric test, Sign test, Test statistics, Ties, Trinomial test",

author = "Guorui Bian and Michael McAleer and Wing-Keung Wong",

note = "Funding Information: We are grateful to the Editor and two anonymous referees for their substantive comments that have significantly improved this manuscript. For financial support, the first author is grateful to East China Normal University , the second author acknowledges the Australian Research Council , National Science Council , Taiwan, and the Japan Society for the Promotion of Science , and the third author wishes to acknowledge Hong Kong Baptist University .",

year = "2011",

month = feb,

doi = "10.1016/j.matcom.2010.11.002",

language = "English",

volume = "81",

pages = "1153--1160",

journal = "Mathematics and Computers in Simulation",

issn = "0378-4754",

publisher = "Elsevier",

number = "6",

}

TY - JOUR

T1 - A trinomial test for paired data when there are many ties

AU - Bian, Guorui

AU - McAleer, Michael

AU - Wong, Wing-Keung

N1 - Funding Information: We are grateful to the Editor and two anonymous referees for their substantive comments that have significantly improved this manuscript. For financial support, the first author is grateful to East China Normal University , the second author acknowledges the Australian Research Council , National Science Council , Taiwan, and the Japan Society for the Promotion of Science , and the third author wishes to acknowledge Hong Kong Baptist University .

PY - 2011/2

Y1 - 2011/2

N2 - This paper develops a new test, the trinomial test, for pairwise ordinal data samples to improve the power of the sign test by modifying its treatment of zero differences between observations, thereby increasing the use of sample information. Simulations demonstrate the power superiority of the proposed trinomial test statistic over the sign test in small samples in the presence of tie observations. We also show that the proposed trinomial test has substantially higher power than the sign test in large samples and also in the presence of tie observations, as the sign test ignores information from observations resulting in ties.

AB - This paper develops a new test, the trinomial test, for pairwise ordinal data samples to improve the power of the sign test by modifying its treatment of zero differences between observations, thereby increasing the use of sample information. Simulations demonstrate the power superiority of the proposed trinomial test statistic over the sign test in small samples in the presence of tie observations. We also show that the proposed trinomial test has substantially higher power than the sign test in large samples and also in the presence of tie observations, as the sign test ignores information from observations resulting in ties.

KW - Non-parametric test

KW - Sign test

KW - Test statistics

KW - Ties

KW - Trinomial test

UR - http://www.scopus.com/inward/record.url?scp=79551496839&partnerID=8YFLogxK

U2 - 10.1016/j.matcom.2010.11.002

DO - 10.1016/j.matcom.2010.11.002

M3 - Journal article

AN - SCOPUS:79551496839

SN - 0378-4754

VL - 81

SP - 1153

EP - 1160

JO - Mathematics and Computers in Simulation

JF - Mathematics and Computers in Simulation

IS - 6

ER -

A trinomial test for paired data when there are many ties

Abstract

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this