New confidence intervals for the proportion of interest in one-sample correlated binary data

Seung Ho Kang, Yonghee Lee

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Correlated binary data is obtained in many fields of biomedical research. When constructing a confidence interval for the proportion of interest, asymptotic confidence intervals have already been developed. However, such asymptotic confidence intervals are unreliable in small samples. To improve the performance of asymptotic confidence intervals in small samples, we obtain the Edgeworth expansion of the distribution of the studentized mean of beta-binomial random variables. Then, we propose new asymptotic confidence intervals by correcting the skewness in the Edgeworth expansion in one direct and two indirect ways. New confidence intervals are compared with the existing confidence intervals in simulation studies.

Original languageEnglish
Pages (from-to)2865-2876
Number of pages12
JournalCommunications in Statistics - Theory and Methods
Volume39
Issue number16
DOIs
Publication statusPublished - 2010 Aug 19

Fingerprint

Correlated Binary Data
Confidence interval
Proportion
Edgeworth Expansion
Small Sample
Beta-binomial
Skewness
Random variable
Simulation Study

All Science Journal Classification (ASJC) codes

  • Statistics and Probability

Cite this

@article{d85f16708d114fa2a98921f539c9d5f0,
title = "New confidence intervals for the proportion of interest in one-sample correlated binary data",
abstract = "Correlated binary data is obtained in many fields of biomedical research. When constructing a confidence interval for the proportion of interest, asymptotic confidence intervals have already been developed. However, such asymptotic confidence intervals are unreliable in small samples. To improve the performance of asymptotic confidence intervals in small samples, we obtain the Edgeworth expansion of the distribution of the studentized mean of beta-binomial random variables. Then, we propose new asymptotic confidence intervals by correcting the skewness in the Edgeworth expansion in one direct and two indirect ways. New confidence intervals are compared with the existing confidence intervals in simulation studies.",
author = "Kang, {Seung Ho} and Yonghee Lee",
year = "2010",
month = "8",
day = "19",
doi = "10.1080/03610920903147796",
language = "English",
volume = "39",
pages = "2865--2876",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",
number = "16",

}

New confidence intervals for the proportion of interest in one-sample correlated binary data. / Kang, Seung Ho; Lee, Yonghee.

In: Communications in Statistics - Theory and Methods, Vol. 39, No. 16, 19.08.2010, p. 2865-2876.

Research output: Contribution to journalArticle

TY - JOUR

T1 - New confidence intervals for the proportion of interest in one-sample correlated binary data

AU - Kang, Seung Ho

AU - Lee, Yonghee

PY - 2010/8/19

Y1 - 2010/8/19

N2 - Correlated binary data is obtained in many fields of biomedical research. When constructing a confidence interval for the proportion of interest, asymptotic confidence intervals have already been developed. However, such asymptotic confidence intervals are unreliable in small samples. To improve the performance of asymptotic confidence intervals in small samples, we obtain the Edgeworth expansion of the distribution of the studentized mean of beta-binomial random variables. Then, we propose new asymptotic confidence intervals by correcting the skewness in the Edgeworth expansion in one direct and two indirect ways. New confidence intervals are compared with the existing confidence intervals in simulation studies.

AB - Correlated binary data is obtained in many fields of biomedical research. When constructing a confidence interval for the proportion of interest, asymptotic confidence intervals have already been developed. However, such asymptotic confidence intervals are unreliable in small samples. To improve the performance of asymptotic confidence intervals in small samples, we obtain the Edgeworth expansion of the distribution of the studentized mean of beta-binomial random variables. Then, we propose new asymptotic confidence intervals by correcting the skewness in the Edgeworth expansion in one direct and two indirect ways. New confidence intervals are compared with the existing confidence intervals in simulation studies.

UR - http://www.scopus.com/inward/record.url?scp=77955569899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955569899&partnerID=8YFLogxK

U2 - 10.1080/03610920903147796

DO - 10.1080/03610920903147796

M3 - Article

AN - SCOPUS:77955569899

VL - 39

SP - 2865

EP - 2876

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 16

ER -