Bayesian estimation of variance partition coefficients adjusted for imperfect test sensitivity and specificity

Polychronis Kostoulas, Leonidas Leontides, William J. Browne, Ian Gardner

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The variance partition coefficient (VPC) measures the clustering of infection/disease among individuals with a specific covariate pattern. Covariate-pattern-specific VPCs provide insight to the groups of individuals that exhibit great heterogeneity and should be targeted for intervention. VPCs should be taken into consideration when planning study designs, modeling data and estimating sample sizes. We present a Bayesian discrete mixed model for the estimation of covariate-pattern-specific VPCs when measurement of the infection/disease is based on an imperfect test. The utility of the presented model is demonstrated with three applications. In all cases, imperfect tests biased VPC estimates towards the null but corrected estimates could be obtained by modeling the sensitivity and specificity of the test procedure with beta distributions. The comparison of adjusted VPCs between the intercept only and the fitted models with higher level covariates explained the portion of heterogeneity in the data that was accounted for by the covariates.

Original languageEnglish (US)
Pages (from-to)155-162
Number of pages8
JournalPreventive Veterinary Medicine
Volume89
Issue number3-4
DOIs
StatePublished - Jun 1 2009

Fingerprint

partition coefficients
Sensitivity and Specificity
Infection
Sample Size
Cluster Analysis
testing
infection
planning
experimental design
sampling

Keywords

  • Bayesian estimation
  • Paratuberculosis
  • Salmonellosis
  • Sensitivity
  • Specificity
  • Variance partition coefficient

ASJC Scopus subject areas

  • Food Animals
  • Animal Science and Zoology

Cite this

Bayesian estimation of variance partition coefficients adjusted for imperfect test sensitivity and specificity. / Kostoulas, Polychronis; Leontides, Leonidas; Browne, William J.; Gardner, Ian.

In: Preventive Veterinary Medicine, Vol. 89, No. 3-4, 01.06.2009, p. 155-162.

Research output: Contribution to journalArticle

Kostoulas, Polychronis ; Leontides, Leonidas ; Browne, William J. ; Gardner, Ian. / Bayesian estimation of variance partition coefficients adjusted for imperfect test sensitivity and specificity. In: Preventive Veterinary Medicine. 2009 ; Vol. 89, No. 3-4. pp. 155-162.
@article{1a7fcee75be84030bdfd2420b054497a,
title = "Bayesian estimation of variance partition coefficients adjusted for imperfect test sensitivity and specificity",
abstract = "The variance partition coefficient (VPC) measures the clustering of infection/disease among individuals with a specific covariate pattern. Covariate-pattern-specific VPCs provide insight to the groups of individuals that exhibit great heterogeneity and should be targeted for intervention. VPCs should be taken into consideration when planning study designs, modeling data and estimating sample sizes. We present a Bayesian discrete mixed model for the estimation of covariate-pattern-specific VPCs when measurement of the infection/disease is based on an imperfect test. The utility of the presented model is demonstrated with three applications. In all cases, imperfect tests biased VPC estimates towards the null but corrected estimates could be obtained by modeling the sensitivity and specificity of the test procedure with beta distributions. The comparison of adjusted VPCs between the intercept only and the fitted models with higher level covariates explained the portion of heterogeneity in the data that was accounted for by the covariates.",
keywords = "Bayesian estimation, Paratuberculosis, Salmonellosis, Sensitivity, Specificity, Variance partition coefficient",
author = "Polychronis Kostoulas and Leonidas Leontides and Browne, {William J.} and Ian Gardner",
year = "2009",
month = "6",
day = "1",
doi = "10.1016/j.prevetmed.2009.02.008",
language = "English (US)",
volume = "89",
pages = "155--162",
journal = "Preventive Veterinary Medicine",
issn = "0167-5877",
publisher = "Elsevier",
number = "3-4",

}

TY - JOUR

T1 - Bayesian estimation of variance partition coefficients adjusted for imperfect test sensitivity and specificity

AU - Kostoulas, Polychronis

AU - Leontides, Leonidas

AU - Browne, William J.

AU - Gardner, Ian

PY - 2009/6/1

Y1 - 2009/6/1

N2 - The variance partition coefficient (VPC) measures the clustering of infection/disease among individuals with a specific covariate pattern. Covariate-pattern-specific VPCs provide insight to the groups of individuals that exhibit great heterogeneity and should be targeted for intervention. VPCs should be taken into consideration when planning study designs, modeling data and estimating sample sizes. We present a Bayesian discrete mixed model for the estimation of covariate-pattern-specific VPCs when measurement of the infection/disease is based on an imperfect test. The utility of the presented model is demonstrated with three applications. In all cases, imperfect tests biased VPC estimates towards the null but corrected estimates could be obtained by modeling the sensitivity and specificity of the test procedure with beta distributions. The comparison of adjusted VPCs between the intercept only and the fitted models with higher level covariates explained the portion of heterogeneity in the data that was accounted for by the covariates.

AB - The variance partition coefficient (VPC) measures the clustering of infection/disease among individuals with a specific covariate pattern. Covariate-pattern-specific VPCs provide insight to the groups of individuals that exhibit great heterogeneity and should be targeted for intervention. VPCs should be taken into consideration when planning study designs, modeling data and estimating sample sizes. We present a Bayesian discrete mixed model for the estimation of covariate-pattern-specific VPCs when measurement of the infection/disease is based on an imperfect test. The utility of the presented model is demonstrated with three applications. In all cases, imperfect tests biased VPC estimates towards the null but corrected estimates could be obtained by modeling the sensitivity and specificity of the test procedure with beta distributions. The comparison of adjusted VPCs between the intercept only and the fitted models with higher level covariates explained the portion of heterogeneity in the data that was accounted for by the covariates.

KW - Bayesian estimation

KW - Paratuberculosis

KW - Salmonellosis

KW - Sensitivity

KW - Specificity

KW - Variance partition coefficient

UR - http://www.scopus.com/inward/record.url?scp=64949088214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=64949088214&partnerID=8YFLogxK

U2 - 10.1016/j.prevetmed.2009.02.008

DO - 10.1016/j.prevetmed.2009.02.008

M3 - Article

C2 - 19297045

AN - SCOPUS:64949088214

VL - 89

SP - 155

EP - 162

JO - Preventive Veterinary Medicine

JF - Preventive Veterinary Medicine

SN - 0167-5877

IS - 3-4

ER -