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

Reliability studies can be designed more efficiently by using variance components estimates from different sources.

Anne M Euser1, Saskia le Cessie, Martijn J J Finken

  • 1Department of Clinical Epidemiology, Leiden University Medical Center, Albinusdreef 2, P.O.Box 9600, 2300 RC Leiden, The Netherlands.

Journal of Clinical Epidemiology
|September 22, 2007
PubMed
Summary
This summary is machine-generated.

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

Similar predictive performance and clinical utility of the Kidney Failure Risk Equation using EKFC or CKD-EPI estimated glomerular filtration rate.

Clinical kidney journal·2026
Same author

Erratum to Impact of Prior Kidney Transplantation on Symptom Burden and Health-Related Quality of Life in Incident Dialysis Patients (Kid Med. 2026;8(6):101357).

Kidney medicine·2026
Same author

Measured and Estimated Glomerular Filtration Rates and Risk of Adverse Health Outcomes.

JAMA·2026
Same author

Impact of Prior Kidney Transplantation on Symptom Burden and Health-Related Quality of Life in Incident Dialysis Patients.

Kidney medicine·2026
Same author

Learning Needs Assessment Among Indonesian Dental Schools' Teachers for Teaching Evidence-Based Practice.

Advances in medical education and practice·2026
Same author

Vascular Access Surgery Timing: A Prospective European Cohort Study in Elderly Patients with ESKD.

Kidney360·2026

Combining data from small reliability studies with larger studies improves the estimation of intra-class correlation coefficients (ICCs). This approach yields more precise ICCs for interobserver reliability, enhancing data analysis in multicenter research.

Area of Science:

  • Biostatistics
  • Clinical Research Methodology

Background:

  • Reliability studies are often embedded within larger multicenter studies, but data from the main study are underutilized for estimating interobserver reliability.
  • Traditional methods for calculating intra-class correlation coefficients (ICCs) often rely solely on limited data from the reliability substudy.

Purpose of the Study:

  • To highlight the advantages of integrating data from both reliability substudies and the main study to enhance the precision of ICC estimation.
  • To improve the accuracy of interobserver reliability assessments in large-scale research projects.

Main Methods:

  • Employed three distinct approaches for calculating ICCs: a classical method using only reliability study data, a combined variances approach incorporating main study variances, and a maximum likelihood approach utilizing all available data.

Related Experiment Videos

  • Applied these methods to estimate fat percentages within the Project On Preterm and Small-for-gestational-age infants-19 (POPS-19) study and through simulations.

    • Main Results:

    • The combined variances and maximum likelihood approaches yielded higher ICCs (0.94, 95% CI [0.90, 0.97] and 0.94, 95% CI [0.88, 0.97], respectively) compared to the classical approach (0.84, 95% CI [0.57, 0.99]).
    • Demonstrated that integrating data from the larger study significantly improves ICC precision.

    Conclusions:

    • Efficiently combining data from small reliability studies with the main study data leads to more precise ICC estimates.
    • This integrated approach enhances the reliability assessment in multicenter studies, offering more robust statistical power.