Application of anbar's approach to hypothesis testing to detect the difference between two proportions

Julia N Soulakova, Ananya Roy

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this paper, Anbar's (1983) approach for estimating a difference between two binomial proportions is discussed with respect to a hypothesis testing problem. Such an approach results in two possible testing strategies. While the results of the tests are expected to agree for a large sample size when two proportions are equal, the tests are shown to perform quite differently in terms of their probabilities of a Type I error for selected sample sizes. Moreover, the tests can lead to different conclusions, which is illustrated via a simple example; and the probability of such cases can be relatively large. In an attempt to improve the tests while preserving their relative simplicity feature, a modified test is proposed. The performance of this test and a conventional test based on normal approximation is assessed. It is shown that the modified Anbar's test better controls the probability of a Type I error for moderate sample sizes.

Original languageEnglish (US)
Pages (from-to)1866-1878
Number of pages13
JournalCommunications in Statistics - Theory and Methods
Volume40
Issue number10
DOIs
StatePublished - Jan 1 2011

Fingerprint

Hypothesis Testing
Proportion
Sample Size
Type I error
Normal Approximation
Simplicity
Testing

Keywords

  • Binomial distribution
  • Large sample
  • Normal approximation

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

Application of anbar's approach to hypothesis testing to detect the difference between two proportions. / Soulakova, Julia N; Roy, Ananya.

In: Communications in Statistics - Theory and Methods, Vol. 40, No. 10, 01.01.2011, p. 1866-1878.

Research output: Contribution to journalArticle

@article{b02ded252fb54557b60f8f95f5e3b95b,
title = "Application of anbar's approach to hypothesis testing to detect the difference between two proportions",
abstract = "In this paper, Anbar's (1983) approach for estimating a difference between two binomial proportions is discussed with respect to a hypothesis testing problem. Such an approach results in two possible testing strategies. While the results of the tests are expected to agree for a large sample size when two proportions are equal, the tests are shown to perform quite differently in terms of their probabilities of a Type I error for selected sample sizes. Moreover, the tests can lead to different conclusions, which is illustrated via a simple example; and the probability of such cases can be relatively large. In an attempt to improve the tests while preserving their relative simplicity feature, a modified test is proposed. The performance of this test and a conventional test based on normal approximation is assessed. It is shown that the modified Anbar's test better controls the probability of a Type I error for moderate sample sizes.",
keywords = "Binomial distribution, Large sample, Normal approximation",
author = "Soulakova, {Julia N} and Ananya Roy",
year = "2011",
month = "1",
day = "1",
doi = "10.1080/03610921003714154",
language = "English (US)",
volume = "40",
pages = "1866--1878",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",
number = "10",

}

TY - JOUR

T1 - Application of anbar's approach to hypothesis testing to detect the difference between two proportions

AU - Soulakova, Julia N

AU - Roy, Ananya

PY - 2011/1/1

Y1 - 2011/1/1

N2 - In this paper, Anbar's (1983) approach for estimating a difference between two binomial proportions is discussed with respect to a hypothesis testing problem. Such an approach results in two possible testing strategies. While the results of the tests are expected to agree for a large sample size when two proportions are equal, the tests are shown to perform quite differently in terms of their probabilities of a Type I error for selected sample sizes. Moreover, the tests can lead to different conclusions, which is illustrated via a simple example; and the probability of such cases can be relatively large. In an attempt to improve the tests while preserving their relative simplicity feature, a modified test is proposed. The performance of this test and a conventional test based on normal approximation is assessed. It is shown that the modified Anbar's test better controls the probability of a Type I error for moderate sample sizes.

AB - In this paper, Anbar's (1983) approach for estimating a difference between two binomial proportions is discussed with respect to a hypothesis testing problem. Such an approach results in two possible testing strategies. While the results of the tests are expected to agree for a large sample size when two proportions are equal, the tests are shown to perform quite differently in terms of their probabilities of a Type I error for selected sample sizes. Moreover, the tests can lead to different conclusions, which is illustrated via a simple example; and the probability of such cases can be relatively large. In an attempt to improve the tests while preserving their relative simplicity feature, a modified test is proposed. The performance of this test and a conventional test based on normal approximation is assessed. It is shown that the modified Anbar's test better controls the probability of a Type I error for moderate sample sizes.

KW - Binomial distribution

KW - Large sample

KW - Normal approximation

UR - http://www.scopus.com/inward/record.url?scp=79952995993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952995993&partnerID=8YFLogxK

U2 - 10.1080/03610921003714154

DO - 10.1080/03610921003714154

M3 - Article

VL - 40

SP - 1866

EP - 1878

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 10

ER -