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

Regression analysis in biological research: sample size and statistical power.

D S Sharp1, P M Gahlinger

  • 1Northern California Occupational Health Center, San Francisco General Medical Center, University of California 94110.

Medicine and Science in Sports and Exercise
|December 1, 1988
PubMed
Summary

Statistical power is crucial in regression analysis. Insufficient power can lead to false negatives, suggesting no relationship exists when one is present, impacting biological research findings.

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

Platelet and Erythrocyte Volume and Count: Epidemiological Predictors of Impedance Measured ADP-Induced Platelet Aggregation in Whole Blood.

Platelets·2010
Same author

Platelet aggregation in whole blood is a paradoxical predictor of ischaemic stroke: Caerphilly Prospective Study revisited.

Platelets·2005
Same author

Environmental influences on helminthiasis and nutritional status among Pacific schoolchildren.

International journal of environmental health research·2004
Same author

A prospective study of HDL-C and cholesteryl ester transfer protein gene mutations and the risk of coronary heart disease in the elderly.

Journal of lipid research·2004
Same author

Quantification of regional glial fibrillary acidic protein levels in Alzheimer's disease.

Acta neurologica Scandinavica·2003
Same author

Random sampling or 'random' model in skin flux measurements? [Commentary on "Investigation of the mechanism of flux across human skin in vitro by quantitative structure-permeability relationships"].

European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences·2001

Area of Science:

  • Biostatistics
  • Physiology
  • Morphology

Background:

  • Regression analysis is commonly employed to establish associations between biologically related variables.
  • Failure to detect significant relationships may stem from true independence or insufficient statistical power.
  • Interpreting non-significant findings requires careful consideration of potential undetected relationships.

Purpose of the Study:

  • To highlight the critical role of statistical power in regression analysis.
  • To emphasize the consequences of underestimating statistical power in biological research.
  • To illustrate the interplay between effect size, alpha error, sample size, and beta error.

Main Methods:

  • The study discusses the fundamental components of statistical inference: effect size, Type I (alpha) error, sample size, and Type II (beta) error.

Related Experiment Videos

  • It examines how these factors influence the detection of relationships in regression models.
  • A practical example using published data is presented to demonstrate the concepts.

    • Main Results:

    • Inadequate statistical power can lead to a Type II (beta) error, failing to detect a true relationship.
    • The probability of detecting a true relationship is influenced by the magnitude of the effect size, alpha error, and sample size.
    • Failure to achieve statistical significance is often misinterpreted as evidence of no biological relationship.

    Conclusions:

    • Investigators must account for statistical power to avoid erroneous conclusions about biological relationships.
    • Understanding the relationship between effect size, alpha, sample size, and beta is essential for robust statistical analysis.
    • Properly assessing statistical power enhances the reliability of findings in biological and physiological research.