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

The meta-analysis of partial effect sizes.

Stephen P Keef1, Leigh A Roberts

  • 1Faculty of Commerce and Administration, Victoria University of Wellington,New Zealand. Stephen.Keef@vuw.ac.nz

The British Journal of Mathematical and Statistical Psychology
|June 3, 2004
PubMed
Summary

This study synthesizes partial effect sizes from multivariate data, extending statistical properties for meta-analysis. Findings aid in comparing effect sizes across studies with different covariates, like gender performance in economics.

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

Injury patterns in elite preprofessional ballet dancers and the utility of screening programs to identify risk characteristics.

The Journal of orthopaedic and sports physical therapyยท2008
See all related articles

Area of Science:

  • Statistics
  • Psychometrics
  • Educational Research

Background:

  • Synthesizing effect sizes is crucial for meta-analysis.
  • Multivariate settings present unique challenges in effect size calculation and comparison.
  • Existing methods may not adequately address varying covariate sets across studies.

Purpose of the Study:

  • To derive general statistical properties of partial d-effect sizes in multivariate contexts.
  • To extend Hedges's zero-order properties for broader applicability.
  • To provide a framework for synthesizing independent effect sizes from studies with differing covariates.

Main Methods:

  • Derivation of general statistical properties for partial d-effect sizes.
  • Application of these properties to a meta-analysis of gender performance differences.

Related Experiment Videos

  • Utilizing Spearman's model of general and specific academic ability.

    • Main Results:

    • Established general statistical properties for partial d-effect sizes.
    • Demonstrated the relevance of these properties for synthesizing independent effect sizes.
    • Addressed the comparison of effect sizes from models with differing covariates.

    Conclusions:

    • The derived properties offer a robust method for synthesizing partial effect sizes in meta-analysis.
    • The approach is applicable to diverse research areas, including educational psychology and economics.
    • Facilitates more accurate comparisons of effect sizes across studies with varied statistical models.