A Test of Simultaneous Homogeneity Against Ordered Alternatives in Multifactorial Design

D. D. Sarath Kulatunga, Shoichi Sasabuchi

研究成果: ジャーナルへの寄稿記事

3 引用 (Scopus)

抄録

A test of simultaneous homogeneity of main effects of several factors against an alternative hypothesis with simple order restrictions in main effects of more than one factor in a multifactorial design is considered. This can be regarded as an extension of Shoracks (1967) work where the alternative hypothesis involves simple order restriction in main effects of one factor. We derive the likelihood ratio test statistic, E-2, and its null hypothesis distribution which involves the convolutions of probabilities P(l, k) used in the statistical inference under order restriction. The powers of the E-2 test and the usual F test are compared by simulation.

元の言語英語
ページ(範囲)3173-3183
ページ数11
ジャーナルCommunications in Statistics - Theory and Methods
13
発行部数25
DOI
出版物ステータス出版済み - 1 1 1984

Fingerprint

Ordered Alternatives
Order Restriction
Main Effect
Homogeneity
Likelihood Ratio Test Statistic
F Test
Alternatives
Statistical Inference
Null hypothesis
Convolution
Design
Simulation

All Science Journal Classification (ASJC) codes

  • Statistics and Probability

これを引用

A Test of Simultaneous Homogeneity Against Ordered Alternatives in Multifactorial Design. / Sarath Kulatunga, D. D.; Sasabuchi, Shoichi.

:: Communications in Statistics - Theory and Methods, 巻 13, 番号 25, 01.01.1984, p. 3173-3183.

研究成果: ジャーナルへの寄稿記事

Sarath Kulatunga, D. D. ; Sasabuchi, Shoichi. / A Test of Simultaneous Homogeneity Against Ordered Alternatives in Multifactorial Design. :: Communications in Statistics - Theory and Methods. 1984 ; 巻 13, 番号 25. pp. 3173-3183.
@article{233911b2103449b197b5efa799fc7267,
title = "A Test of Simultaneous Homogeneity Against Ordered Alternatives in Multifactorial Design",
abstract = "A test of simultaneous homogeneity of main effects of several factors against an alternative hypothesis with simple order restrictions in main effects of more than one factor in a multifactorial design is considered. This can be regarded as an extension of Shoracks (1967) work where the alternative hypothesis involves simple order restriction in main effects of one factor. We derive the likelihood ratio test statistic, E-2, and its null hypothesis distribution which involves the convolutions of probabilities P(l, k) used in the statistical inference under order restriction. The powers of the E-2 test and the usual F test are compared by simulation.",
author = "{Sarath Kulatunga}, {D. D.} and Shoichi Sasabuchi",
year = "1984",
month = "1",
day = "1",
doi = "10.1080/03610928408828885",
language = "English",
volume = "13",
pages = "3173--3183",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",
number = "25",

}

TY - JOUR

T1 - A Test of Simultaneous Homogeneity Against Ordered Alternatives in Multifactorial Design

AU - Sarath Kulatunga, D. D.

AU - Sasabuchi, Shoichi

PY - 1984/1/1

Y1 - 1984/1/1

N2 - A test of simultaneous homogeneity of main effects of several factors against an alternative hypothesis with simple order restrictions in main effects of more than one factor in a multifactorial design is considered. This can be regarded as an extension of Shoracks (1967) work where the alternative hypothesis involves simple order restriction in main effects of one factor. We derive the likelihood ratio test statistic, E-2, and its null hypothesis distribution which involves the convolutions of probabilities P(l, k) used in the statistical inference under order restriction. The powers of the E-2 test and the usual F test are compared by simulation.

AB - A test of simultaneous homogeneity of main effects of several factors against an alternative hypothesis with simple order restrictions in main effects of more than one factor in a multifactorial design is considered. This can be regarded as an extension of Shoracks (1967) work where the alternative hypothesis involves simple order restriction in main effects of one factor. We derive the likelihood ratio test statistic, E-2, and its null hypothesis distribution which involves the convolutions of probabilities P(l, k) used in the statistical inference under order restriction. The powers of the E-2 test and the usual F test are compared by simulation.

UR - http://www.scopus.com/inward/record.url?scp=84936145190&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84936145190&partnerID=8YFLogxK

U2 - 10.1080/03610928408828885

DO - 10.1080/03610928408828885

M3 - Article

VL - 13

SP - 3173

EP - 3183

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 25

ER -