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

Estimating sensitivity and specificity when repeated tests are performed on the same subject.

G Ronco1, A Biggeri

  • 1Unit of Cancer Epidemiology, Department of Oncology, Torino, Italy.

Journal of Epidemiology and Biostatistics
|April 14, 2000
PubMed
Summary

When repeating diagnostic tests, accounting for correlated results is crucial for accurate interval estimates. This study proposes regression techniques for logistic models to improve precision in repeated measures analysis.

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

Sinonasal cancer incidence in Lombardy, Italy, 2008-20.

Occupational medicine (Oxford, England)·2024
Same author

Signatures of the Optical Stark Effect on Entangled Photon Pairs from Resonantly Pumped Quantum Dots.

Physical review letters·2023
Same author

Five-year risk of CIN3 after short-term HPV-DNA negativity in cytology-negative women: a population-based cohort study.

BJOG : an international journal of obstetrics and gynaecology·2019
Same author

Incidence of traumatic spinal cord injury in Italy during 2013-2014: a population-based study.

Spinal cord·2017
Same author

Fine airborne particles: when alarming levels are the standard.

Public health·2017
Same author

Daily peer review of abnormal cervical smears in the assessment of individual practice as an additional method of internal quality control.

Cytopathology : official journal of the British Society for Clinical Cytology·2014

Area of Science:

  • Biostatistics
  • Medical Diagnostics
  • Statistical Modeling

Background:

  • Repeated diagnostic tests on the same subject inherently yield correlated results.
  • Accurate interval estimates require statistical methods that account for this correlation.
  • Ignoring test result correlation can lead to biased estimations.

Purpose of the Study:

  • To propose regression techniques for correlated data within a logistic model framework.
  • To achieve correct point and interval estimates for diagnostic tests with repeated measures.
  • To enhance the statistical rigor of analyzing repeated diagnostic test outcomes.

Main Methods:

  • Application of regression techniques tailored for correlated data.
  • Utilizing a logistic model to handle binary or dichotomous test outcomes.

Related Experiment Videos

  • Exploration of marginal and 'random effects' models for analysis.

    • Main Results:

    • Demonstration of corrected point and interval estimates using proposed methods.
    • Discussion of various study designs and their impact on analysis.
    • Identification and correction strategies for potential biases in multiple testing scenarios.
    • Illustrative example using Doppler flow velocimetry in pregnancy.

    Conclusions:

    • Regression techniques for correlated data in logistic models provide accurate estimates.
    • Careful consideration of study design and bias is essential for repeated diagnostic testing.
    • The proposed methods offer a robust approach to analyzing correlated diagnostic test results.