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

Statistical validity of using ratio variables in human kinetics research.

Yuanlong Liu1, Robert W Schutz

  • 1Department of Health, Physical Education, and Recreation at Western Michigan University, Kalamazoo 49006, USA. yuanlong.liu@wmich.edu

Research Quarterly for Exercise and Sport
|September 27, 2003
PubMed
Summary

Researchers should test multiple deflation models for ratio variables, as no single model fits all data. The reliability of ratio scores depends on component variable characteristics, not just individual measure reliability.

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

TeCYC2c functions as a hub protein in the CYC2 gene cluster to regulate ray floret development in marigold (Tagetes erecta).

The Plant journal : for cell and molecular biology·2026
Same author

Microwave-assisted technologies for recycling and regeneration of spent lithium-ion batteries.

Frontiers in chemistry·2026
Same author

Interpretable machine learning and deep learning model for discriminating pheochromocytoma from adrenocortical adenoma based on CT: A multicenter study.

European journal of radiology·2026
Same author

HaploC-tools reveal haplotype-specific chromosome conformation and chromatin states.

Nature communications·2026
Same author

AI-driven fungicide design: From target identification to field application.

Plant communications·2026
Same author

Validation of the Transformer-Based Monocular System (Capture4D): A Real-Time Kinematic Analysis in Coaching/Teaching Tennis.

Sensors (Basel, Switzerland)·2026

Area of Science:

  • Statistics
  • Data Analysis

Background:

  • Ratio variables are common in research.
  • Assessing the reliability of ratio variables is crucial for valid interpretation.

Purpose of the Study:

  • To evaluate the validity of simple ratio and deflation models.
  • To determine how variable characteristics impact ratio reliability.

Main Methods:

  • Fitted simple ratio and three deflation models to four datasets.
  • Used Intraclass Correlation to assess component variable effects.
  • Applied standard criteria for model selection.

Main Results:

  • Deflation model validity is data-dependent.
  • An optimal model for all ratio variables may not exist.

Related Experiment Videos

  • Ratio reliability is influenced by coefficient of variation and component correlations.

    • Conclusions:

    • Researchers must test various models for each dataset.
    • Calculate reliability for derived ratio scores.
    • Do not assume high component reliability ensures high ratio reliability.