Sample size determination for estimation of the accuracy of two conditionally independent tests in the absence of a gold standard

Marios P. Georgiadis, Wesley O. Johnson, Ian Gardner

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

We developed an Excel spreadsheet template (available at http://www.epi.ucdavis.edu/diagnostictests/) to calculate sample sizes to estimate sensitivity and specificity with desired precision in the absence of a gold standard. Calculations are predicated on the use of two conditionally independent tests for screening animals from two populations and are based on the methods of Hui and Walter (1980). Sample size calculations rely on asymptotic normality of maximum likelihood (ML) estimates of parameters. Spreadsheets for calculating standard errors for the parameter estimates and for providing ML estimates using cross-tabulated data also are included. An example of application of the methods to bovine paratuberculosis is presented.

Original languageEnglish (US)
Pages (from-to)1-10
Number of pages10
JournalPreventive Veterinary Medicine
Volume71
Issue number1-2
DOIs
StatePublished - Sep 30 2005

Fingerprint

Likelihood Functions
Sample Size
gold
Paratuberculosis
paratuberculosis
application methods
testing
screening
Sensitivity and Specificity
sampling
cattle
Population
animals
methodology

Keywords

  • Hui and Walter model
  • Prevalence
  • Sample size
  • Sensitivity
  • Specificity

ASJC Scopus subject areas

  • Food Animals
  • Animal Science and Zoology

Cite this

Sample size determination for estimation of the accuracy of two conditionally independent tests in the absence of a gold standard. / Georgiadis, Marios P.; Johnson, Wesley O.; Gardner, Ian.

In: Preventive Veterinary Medicine, Vol. 71, No. 1-2, 30.09.2005, p. 1-10.

Research output: Contribution to journalArticle

@article{82700510197948219f10b0a71131a0bc,
title = "Sample size determination for estimation of the accuracy of two conditionally independent tests in the absence of a gold standard",
abstract = "We developed an Excel spreadsheet template (available at http://www.epi.ucdavis.edu/diagnostictests/) to calculate sample sizes to estimate sensitivity and specificity with desired precision in the absence of a gold standard. Calculations are predicated on the use of two conditionally independent tests for screening animals from two populations and are based on the methods of Hui and Walter (1980). Sample size calculations rely on asymptotic normality of maximum likelihood (ML) estimates of parameters. Spreadsheets for calculating standard errors for the parameter estimates and for providing ML estimates using cross-tabulated data also are included. An example of application of the methods to bovine paratuberculosis is presented.",
keywords = "Hui and Walter model, Prevalence, Sample size, Sensitivity, Specificity",
author = "Georgiadis, {Marios P.} and Johnson, {Wesley O.} and Ian Gardner",
year = "2005",
month = "9",
day = "30",
doi = "10.1016/j.prevetmed.2005.04.004",
language = "English (US)",
volume = "71",
pages = "1--10",
journal = "Preventive Veterinary Medicine",
issn = "0167-5877",
publisher = "Elsevier",
number = "1-2",

}

TY - JOUR

T1 - Sample size determination for estimation of the accuracy of two conditionally independent tests in the absence of a gold standard

AU - Georgiadis, Marios P.

AU - Johnson, Wesley O.

AU - Gardner, Ian

PY - 2005/9/30

Y1 - 2005/9/30

N2 - We developed an Excel spreadsheet template (available at http://www.epi.ucdavis.edu/diagnostictests/) to calculate sample sizes to estimate sensitivity and specificity with desired precision in the absence of a gold standard. Calculations are predicated on the use of two conditionally independent tests for screening animals from two populations and are based on the methods of Hui and Walter (1980). Sample size calculations rely on asymptotic normality of maximum likelihood (ML) estimates of parameters. Spreadsheets for calculating standard errors for the parameter estimates and for providing ML estimates using cross-tabulated data also are included. An example of application of the methods to bovine paratuberculosis is presented.

AB - We developed an Excel spreadsheet template (available at http://www.epi.ucdavis.edu/diagnostictests/) to calculate sample sizes to estimate sensitivity and specificity with desired precision in the absence of a gold standard. Calculations are predicated on the use of two conditionally independent tests for screening animals from two populations and are based on the methods of Hui and Walter (1980). Sample size calculations rely on asymptotic normality of maximum likelihood (ML) estimates of parameters. Spreadsheets for calculating standard errors for the parameter estimates and for providing ML estimates using cross-tabulated data also are included. An example of application of the methods to bovine paratuberculosis is presented.

KW - Hui and Walter model

KW - Prevalence

KW - Sample size

KW - Sensitivity

KW - Specificity

UR - http://www.scopus.com/inward/record.url?scp=23944448555&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=23944448555&partnerID=8YFLogxK

U2 - 10.1016/j.prevetmed.2005.04.004

DO - 10.1016/j.prevetmed.2005.04.004

M3 - Article

C2 - 16076507

AN - SCOPUS:23944448555

VL - 71

SP - 1

EP - 10

JO - Preventive Veterinary Medicine

JF - Preventive Veterinary Medicine

SN - 0167-5877

IS - 1-2

ER -