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

Assessing reproducibility of data obtained with instruments based on continuous measurements.

M Bédard1, N J Martin, P Krueger

  • 1St. Joseph's Health Care System Research Network, Hamilton, Ontario, Canada. mbedard@baynet.net

Experimental Aging Research
|November 25, 2000
PubMed
Summary

Reliability in aging research requires careful statistical evaluation. Intraclass correlation coefficients (ICC) are the preferred method over Pearson correlations and paired t tests for assessing tool reliability, especially when systematic bias is present.

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

Transosseous suture loop technique for MPFL reconstruction.

Journal of biological regulators and homeostatic agents·2020
Same author

Resuming elective hip and knee arthroplasty after the first phase of the SARS-CoV-2 pandemic: the European Hip Society and European Knee Associates recommendations.

Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA·2020
Same author

Recommendations for resuming elective hip and knee arthroplasty in the setting of the SARS-CoV-2 pandemic: the European Hip Society and European Knee Associates Survey of Members.

Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA·2020
Same author

Driving safety improves after individualized training: An RCT involving older drivers in an urban area.

Traffic injury prevention·2019
Same author

What are the differences among occupational groups related to their palliative care-specific educational needs and intensity of interprofessional collaboration in long-term care homes?

BMC palliative care·2017
Same author

Bilateral distal fibula fractures in a woman on long-term bisphosphonate therapy.

Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA·2015

Area of Science:

  • Gerontology
  • Biostatistics
  • Research Methodology

Background:

  • Reproducibility, or reliability, is crucial for research tool data.
  • Intraclass correlation coefficients (ICC), Pearson correlations, and paired t tests are commonly used for reliability assessment in aging research.
  • These methods are often incorrectly considered interchangeable, potentially leading to flawed instrument selection.

Purpose of the Study:

  • To compare reliability estimates from ICC, Pearson correlations, and paired t tests.
  • To determine the most preferable technique for assessing reliability in aging research.

Main Methods:

  • A hypothetical dataset with 20 observations per participant was generated.
  • Three scenarios were simulated: good agreement, systematic bias, and substantial random measurement error.

Related Experiment Videos

  • Reliability estimates were calculated using ICC, Pearson correlations, and paired t tests for each scenario.

    • Main Results:

    • All methods indicated reliability in the 'good agreement' scenario.
    • In the 'systematic bias' scenario, ICC and t tests showed low reliability, while Pearson correlation indicated high reliability.
    • In the 'random measurement error' scenario, ICC and Pearson accurately reflected low reliability, but the t test suggested high reliability.

    Conclusions:

    • Intraclass correlation coefficients (ICC) are the preferred technique for measuring reliability in aging research.
    • While ICC has limitations, they are manageable, making it superior to Pearson correlations and paired t tests for reliability assessment.