Drawbacks to noninteger scoring for ordered categorical data

Stephen Senn

doi:10.1111/j.1541-0420.2007.00739_1.x

Drawbacks to noninteger scoring for ordered categorical data

Stephen Senn^*

^*Corresponding author for this work

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

15 Citations (Scopus)

Abstract

A proposal to improve trend tests by using noninteger scores is examined. It is concluded that despite improved power such tests are usually inferior to the simpler integer scored approach.

Original language	English
Pages (from-to)	296-298
Number of pages	3
Journal	Biometrics
Volume	63
Issue number	1
DOIs	https://doi.org/10.1111/j.1541-0420.2007.00739_1.x
Publication status	Published - Mar 2007
Externally published	Yes

Keywords

Discrete data
Fisher's exact test
Power
Randomization test
Trend test

Access to Document

10.1111/j.1541-0420.2007.00739_1.x

Cite this

@article{03756c92fdf54f2b8822e527a94cfc93,

title = "Drawbacks to noninteger scoring for ordered categorical data",

abstract = "A proposal to improve trend tests by using noninteger scores is examined. It is concluded that despite improved power such tests are usually inferior to the simpler integer scored approach.",

keywords = "Discrete data, Fisher's exact test, Power, Randomization test, Trend test",

author = "Stephen Senn",

year = "2007",

month = mar,

doi = "10.1111/j.1541-0420.2007.00739\_1.x",

language = "English",

volume = "63",

pages = "296--298",

journal = "Biometrics",

issn = "0006-341X",

publisher = "Oxford University Press",

number = "1",

}

TY - JOUR

T1 - Drawbacks to noninteger scoring for ordered categorical data

AU - Senn, Stephen

PY - 2007/3

Y1 - 2007/3

N2 - A proposal to improve trend tests by using noninteger scores is examined. It is concluded that despite improved power such tests are usually inferior to the simpler integer scored approach.

AB - A proposal to improve trend tests by using noninteger scores is examined. It is concluded that despite improved power such tests are usually inferior to the simpler integer scored approach.

KW - Discrete data

KW - Fisher's exact test

KW - Power

KW - Randomization test

KW - Trend test

UR - https://www.scopus.com/pages/publications/34247205838

U2 - 10.1111/j.1541-0420.2007.00739_1.x

DO - 10.1111/j.1541-0420.2007.00739_1.x

M3 - Review article

C2 - 17447957

AN - SCOPUS:34247205838

SN - 0006-341X

VL - 63

SP - 296

EP - 298

JO - Biometrics

JF - Biometrics

IS - 1

ER -

Drawbacks to noninteger scoring for ordered categorical data

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this