An empirical Bayes group-testing approach to estimating small proportions

Joshua M. Tebbs, Christopher R. Bilder, Barry K. Moser

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Group testing has long been recognized as a safe and sensible alternative to one-at-a-time testing in applications wherein the prevalence rate p is small. In this article, we develop an empirical Bayes (EB) procedure to estimate p using a beta-type prior distribution and a squared-error loss function. We show that the EB estimator is preferred over the usual maximum likelihood estimator (MLE) for small group sizes and small p. In addition, we also discuss interval estimation and consider the use of other loss functions perhaps more appropriate in public health studies. The proposed methods are illustrated using group-testing data from a prospective hepatitis C virus study conducted in Xuzhou City, China.

Original languageEnglish (US)
Pages (from-to)983-995
Number of pages13
JournalCommunications in Statistics - Theory and Methods
Volume32
Issue number5
DOIs
StatePublished - May 1 2003

Fingerprint

Group Testing
Empirical Bayes
Proportion
Bayes Procedures
Squared Error Loss Function
Empirical Bayes Estimator
Interval Estimation
Public Health
Testing
Loss Function
Prior distribution
Maximum Likelihood Estimator
Virus
China
Public health
Viruses
Maximum likelihood
Alternatives
Estimate

Keywords

  • Composite sampling
  • Empirical Bayes estimation
  • Hepatitis C virus
  • Pooling designs
  • Screening experiments

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

An empirical Bayes group-testing approach to estimating small proportions. / Tebbs, Joshua M.; Bilder, Christopher R.; Moser, Barry K.

In: Communications in Statistics - Theory and Methods, Vol. 32, No. 5, 01.05.2003, p. 983-995.

Research output: Contribution to journalArticle

@article{0bded2dc564a43e181d78247f7731986,
title = "An empirical Bayes group-testing approach to estimating small proportions",
abstract = "Group testing has long been recognized as a safe and sensible alternative to one-at-a-time testing in applications wherein the prevalence rate p is small. In this article, we develop an empirical Bayes (EB) procedure to estimate p using a beta-type prior distribution and a squared-error loss function. We show that the EB estimator is preferred over the usual maximum likelihood estimator (MLE) for small group sizes and small p. In addition, we also discuss interval estimation and consider the use of other loss functions perhaps more appropriate in public health studies. The proposed methods are illustrated using group-testing data from a prospective hepatitis C virus study conducted in Xuzhou City, China.",
keywords = "Composite sampling, Empirical Bayes estimation, Hepatitis C virus, Pooling designs, Screening experiments",
author = "Tebbs, {Joshua M.} and Bilder, {Christopher R.} and Moser, {Barry K.}",
year = "2003",
month = "5",
day = "1",
doi = "10.1081/STA-120019957",
language = "English (US)",
volume = "32",
pages = "983--995",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",
number = "5",

}

TY - JOUR

T1 - An empirical Bayes group-testing approach to estimating small proportions

AU - Tebbs, Joshua M.

AU - Bilder, Christopher R.

AU - Moser, Barry K.

PY - 2003/5/1

Y1 - 2003/5/1

N2 - Group testing has long been recognized as a safe and sensible alternative to one-at-a-time testing in applications wherein the prevalence rate p is small. In this article, we develop an empirical Bayes (EB) procedure to estimate p using a beta-type prior distribution and a squared-error loss function. We show that the EB estimator is preferred over the usual maximum likelihood estimator (MLE) for small group sizes and small p. In addition, we also discuss interval estimation and consider the use of other loss functions perhaps more appropriate in public health studies. The proposed methods are illustrated using group-testing data from a prospective hepatitis C virus study conducted in Xuzhou City, China.

AB - Group testing has long been recognized as a safe and sensible alternative to one-at-a-time testing in applications wherein the prevalence rate p is small. In this article, we develop an empirical Bayes (EB) procedure to estimate p using a beta-type prior distribution and a squared-error loss function. We show that the EB estimator is preferred over the usual maximum likelihood estimator (MLE) for small group sizes and small p. In addition, we also discuss interval estimation and consider the use of other loss functions perhaps more appropriate in public health studies. The proposed methods are illustrated using group-testing data from a prospective hepatitis C virus study conducted in Xuzhou City, China.

KW - Composite sampling

KW - Empirical Bayes estimation

KW - Hepatitis C virus

KW - Pooling designs

KW - Screening experiments

UR - http://www.scopus.com/inward/record.url?scp=0038516757&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038516757&partnerID=8YFLogxK

U2 - 10.1081/STA-120019957

DO - 10.1081/STA-120019957

M3 - Article

AN - SCOPUS:0038516757

VL - 32

SP - 983

EP - 995

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 5

ER -