Logical extremes, beta, and the power of the test

James V. Pinto, Pin T Ng, David S Allen

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

There is a potential misuse of the power function under the logical extreme when the null hypothesis is true. The power function is defined to measure the probability of rejecting the null given any value of the parameter being tested. It can be used to obtain the power and the β values only under the alternative hypothesis. When the null is true, the power function can be used to obtain the size of the test. The power and the probability of committing a Type II error are, however, undefined and, hence, the power function should not be used to obtain these value.

Original languageEnglish (US)
JournalJournal of Statistics Education
Volume11
Issue number1
StatePublished - Mar 2003

Fingerprint

Power Function
Extremes
Null
Type II error
Null hypothesis
Values
Logic
Alternatives

Keywords

  • Power function
  • Simulations
  • Type II error

ASJC Scopus subject areas

  • Statistics and Probability
  • Education

Cite this

Logical extremes, beta, and the power of the test. / Pinto, James V.; Ng, Pin T; Allen, David S.

In: Journal of Statistics Education, Vol. 11, No. 1, 03.2003.

Research output: Contribution to journalArticle

@article{75d03f47ad404e0cacf00e858f9125ae,
title = "Logical extremes, beta, and the power of the test",
abstract = "There is a potential misuse of the power function under the logical extreme when the null hypothesis is true. The power function is defined to measure the probability of rejecting the null given any value of the parameter being tested. It can be used to obtain the power and the β values only under the alternative hypothesis. When the null is true, the power function can be used to obtain the size of the test. The power and the probability of committing a Type II error are, however, undefined and, hence, the power function should not be used to obtain these value.",
keywords = "Power function, Simulations, Type II error",
author = "Pinto, {James V.} and Ng, {Pin T} and Allen, {David S}",
year = "2003",
month = "3",
language = "English (US)",
volume = "11",
journal = "Journal of Statistics Education",
issn = "1069-1898",
publisher = "American Statistical Association",
number = "1",

}

TY - JOUR

T1 - Logical extremes, beta, and the power of the test

AU - Pinto, James V.

AU - Ng, Pin T

AU - Allen, David S

PY - 2003/3

Y1 - 2003/3

N2 - There is a potential misuse of the power function under the logical extreme when the null hypothesis is true. The power function is defined to measure the probability of rejecting the null given any value of the parameter being tested. It can be used to obtain the power and the β values only under the alternative hypothesis. When the null is true, the power function can be used to obtain the size of the test. The power and the probability of committing a Type II error are, however, undefined and, hence, the power function should not be used to obtain these value.

AB - There is a potential misuse of the power function under the logical extreme when the null hypothesis is true. The power function is defined to measure the probability of rejecting the null given any value of the parameter being tested. It can be used to obtain the power and the β values only under the alternative hypothesis. When the null is true, the power function can be used to obtain the size of the test. The power and the probability of committing a Type II error are, however, undefined and, hence, the power function should not be used to obtain these value.

KW - Power function

KW - Simulations

KW - Type II error

UR - http://www.scopus.com/inward/record.url?scp=3042531144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3042531144&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:3042531144

VL - 11

JO - Journal of Statistics Education

JF - Journal of Statistics Education

SN - 1069-1898

IS - 1

ER -