Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Efficiency of two-phase designs for prevalence estimation.

R McNamee1

  • 1Biostatistics Group, School of Epidemiology and Health Sciences, University of Manchester, Oxford Road, Manchester M13 9PT, UK. rmcnamee@man.ac.uk

International Journal of Epidemiology
|December 19, 2003
PubMed
Summary

Two-phase population surveys can be cost-effective for estimating disease prevalence. However, the accuracy of the initial screening test fundamentally limits the efficiency gains of this sampling method.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

An Assessment of Radiation-Associated Risks of Mortality from Circulatory Disease in the Cohorts of Mayak and Sellafield Nuclear Workers.

Radiation research·2018
Same author

Effectiveness of the European chromium(vi) directive for cement implementation on occupational allergic contact dermatitis occurrence: assessment in France and the U.K.

The British journal of dermatology·2016
Same author

The impact of national-level interventions to improve hygiene on the incidence of irritant contact dermatitis in healthcare workers: changes in incidence from 1996 to 2012 and interrupted times series analysis.

The British journal of dermatology·2015
Same author

Investigating work-related neoplasia associated with solar radiation.

Occupational medicine (Oxford, England)·2014
Same author

Modifiable and non-modifiable risk factors for poor sperm morphology.

Human reproduction (Oxford, England)·2014
Same author

Long-term safety of unopposed estrogen used by women surviving myocardial infarction: 14-year follow-up of the ESPRIT randomised controlled trial.

BJOG : an international journal of obstetrics and gynaecology·2014

Area of Science:

  • Epidemiology
  • Biostatistics
  • Survey Methodology

Background:

  • Accurate disease prevalence estimation is crucial but often costly, particularly for conditions not requiring healthcare contact.
  • Two-phase population surveys offer a potential solution using a cheap, fallible initial test followed by a gold standard on a subsample.
  • Previous empirical investigations left questions regarding the cost-efficiency of two-phase designs compared to simple random sampling.

Purpose of the Study:

  • To mathematically derive formulas for maximum and minimum cost/standard error reductions in two-phase sampling versus simple random sampling.
  • To elucidate the impact of disease prevalence on the efficiency of two-phase survey designs.
  • To establish clear criteria for the justification of two-phase sampling based on efficiency.

Main Methods:

Related Experiment Videos

  • Mathematical derivation of formulas quantifying efficiency gains.
  • Analysis of the influence of disease prevalence on survey efficiency.
  • Evaluation of the impact of first-stage test accuracy on overall design efficiency.

Main Results:

  • A simple formula was derived for the maximum reduction in cost or standard error achievable with two-phase sampling.
  • A formula for the minimum reduction was also provided, explaining prevalence's influence on efficiency.
  • The sensitivity and specificity of the initial test impose an absolute limit on the efficiency of two-phase designs.

Conclusions:

  • Two-phase sampling efficiency is critically dependent on the accuracy (sensitivity and specificity) of the first-stage test.
  • If the initial test is not sufficiently accurate, two-phase sampling cannot be justified solely on efficiency grounds.
  • The findings provide a mathematical basis for evaluating the cost-effectiveness of two-phase survey designs in disease prevalence studies.