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

How interchangeable are different estimators of effect size?

J W Ray1, W R Shadish

  • 1Department of Psychology, University of Memphis, Tennessee 38152, USA.

Journal of Consulting and Clinical Psychology
|December 1, 1996
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

The effects of psychological therapies under clinically representative conditions: a meta-analysis.

Psychological bulletin·2000
Same author

Does Alcoholics Anonymous work? The results from a meta-analysis of controlled experiments.

Substance use & misuse·1999
Same author

The prospective relationships between smoking and weight in a young, biracial cohort: the Coronary Artery Risk Development in Young Adults Study.

Journal of consulting and clinical psychology·1999
Same author

Preliminary development of the Children's Physical Self-Concept Scale.

Journal of developmental and behavioral pediatrics : JDBP·1998
Same author

Outcome, attrition, and family-couples treatment for drug abuse: a meta-analysis and review of the controlled, comparative studies.

Psychological bulletin·1997
Same author

Evidence that therapy works in clinically representative conditions.

Journal of consulting and clinical psychology·1997

Estimating effect sizes in meta-analysis is common when direct data is missing. However, this study found that these estimated effect sizes often differ significantly from the true standardized mean difference (d), potentially biasing results.

Area of Science:

  • Psychology
  • Medical Research
  • Biostatistics

Background:

  • Effect size computation is crucial for meta-analysis.
  • Standardized mean difference (d) is the typical effect size for treatment outcomes.
  • Methods exist to estimate 'd' when primary data is insufficient.

Purpose of the Study:

  • To empirically investigate the accuracy of estimated effect sizes compared to 'd'.
  • To determine if commonly used estimation methods accurately reflect the population parameter 'd'.

Main Methods:

  • Analysis of 140 psychosocial treatment or prevention studies.
  • Comparison of computed 'd' with various estimated 'd' values.
  • Assessment of both mean and variance equivalence.

Related Experiment Videos

Main Results:

  • Estimated effect sizes were frequently not equivalent to 'd' in mean.
  • Variances of estimated effect sizes also often differed from 'd'.
  • This suggests potential inaccuracies in meta-analyses relying on these estimates.

Conclusions:

  • Mixing 'd' with other estimates of 'd' in meta-analyses may lead to biased effect size calculations.
  • Inaccurate effect size estimates can result in unreliable significance testing.
  • Researchers should exercise caution when using estimated effect sizes in meta-analyses.