Hierarchical models for estimating herd prevalence and test accuracy in the absence of a gold standard

Timothy Hanson, Wesley O. Johnson, Ian Gardner

Research output: Contribution to journalArticle

58 Citations (Scopus)

Abstract

A common assumption made in studies involving two or more binary diagnostic tests in the absence of a gold standard is one of conditional independence among tests given disease status. Although reasonable in some cases, often this assumption is untenable or untested and may lead to biased results. We propose a class of hierarchical models for the purpose of estimating the herd-level prevalence distribution and the accuracies of two tests in the absence of a gold standard when several exchangeable populations with differing disease prevalence are available for sampling, relaxing the assumption of conditional independence between tests. The models are used to estimate the prevalence of bovine brucellosis in Mexican cow herds and to estimate the error rates of two tests for the detection of swine pneumonia.

Original languageEnglish (US)
Pages (from-to)223-239
Number of pages17
JournalJournal of Agricultural, Biological, and Environmental Statistics
Volume8
Issue number2
DOIs
StatePublished - Jun 1 2003

Fingerprint

Hierarchical Model
Gold
gold
Conditional Independence
herds
Bovine Brucellosis
Independence Test
Conditional Test
Diagnostic Tests
testing
Sampling
bovine brucellosis
Routine Diagnostic Tests
Estimate
brucellosis
Biased
Error Rate
disease prevalence
Pneumonia
Swine

Keywords

  • Sensitivity
  • Specificity

ASJC Scopus subject areas

  • Statistics and Probability
  • Environmental Science(all)
  • Agricultural and Biological Sciences (miscellaneous)
  • Agricultural and Biological Sciences(all)
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Cite this

Hierarchical models for estimating herd prevalence and test accuracy in the absence of a gold standard. / Hanson, Timothy; Johnson, Wesley O.; Gardner, Ian.

In: Journal of Agricultural, Biological, and Environmental Statistics, Vol. 8, No. 2, 01.06.2003, p. 223-239.

Research output: Contribution to journalArticle

@article{864d65a389b34122af7e5d17fd53969b,
title = "Hierarchical models for estimating herd prevalence and test accuracy in the absence of a gold standard",
abstract = "A common assumption made in studies involving two or more binary diagnostic tests in the absence of a gold standard is one of conditional independence among tests given disease status. Although reasonable in some cases, often this assumption is untenable or untested and may lead to biased results. We propose a class of hierarchical models for the purpose of estimating the herd-level prevalence distribution and the accuracies of two tests in the absence of a gold standard when several exchangeable populations with differing disease prevalence are available for sampling, relaxing the assumption of conditional independence between tests. The models are used to estimate the prevalence of bovine brucellosis in Mexican cow herds and to estimate the error rates of two tests for the detection of swine pneumonia.",
keywords = "Sensitivity, Specificity",
author = "Timothy Hanson and Johnson, {Wesley O.} and Ian Gardner",
year = "2003",
month = "6",
day = "1",
doi = "10.1198/1085711031526",
language = "English (US)",
volume = "8",
pages = "223--239",
journal = "Journal of Agricultural, Biological, and Environmental Statistics",
issn = "1085-7117",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - Hierarchical models for estimating herd prevalence and test accuracy in the absence of a gold standard

AU - Hanson, Timothy

AU - Johnson, Wesley O.

AU - Gardner, Ian

PY - 2003/6/1

Y1 - 2003/6/1

N2 - A common assumption made in studies involving two or more binary diagnostic tests in the absence of a gold standard is one of conditional independence among tests given disease status. Although reasonable in some cases, often this assumption is untenable or untested and may lead to biased results. We propose a class of hierarchical models for the purpose of estimating the herd-level prevalence distribution and the accuracies of two tests in the absence of a gold standard when several exchangeable populations with differing disease prevalence are available for sampling, relaxing the assumption of conditional independence between tests. The models are used to estimate the prevalence of bovine brucellosis in Mexican cow herds and to estimate the error rates of two tests for the detection of swine pneumonia.

AB - A common assumption made in studies involving two or more binary diagnostic tests in the absence of a gold standard is one of conditional independence among tests given disease status. Although reasonable in some cases, often this assumption is untenable or untested and may lead to biased results. We propose a class of hierarchical models for the purpose of estimating the herd-level prevalence distribution and the accuracies of two tests in the absence of a gold standard when several exchangeable populations with differing disease prevalence are available for sampling, relaxing the assumption of conditional independence between tests. The models are used to estimate the prevalence of bovine brucellosis in Mexican cow herds and to estimate the error rates of two tests for the detection of swine pneumonia.

KW - Sensitivity

KW - Specificity

UR - http://www.scopus.com/inward/record.url?scp=0141754238&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0141754238&partnerID=8YFLogxK

U2 - 10.1198/1085711031526

DO - 10.1198/1085711031526

M3 - Article

AN - SCOPUS:0141754238

VL - 8

SP - 223

EP - 239

JO - Journal of Agricultural, Biological, and Environmental Statistics

JF - Journal of Agricultural, Biological, and Environmental Statistics

SN - 1085-7117

IS - 2

ER -