Statistical properties of four effect-size measures for mediation models

Milica Miočević, Holly O'Rourke, David Mackinnon, Hendricks C. Brown

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

This project examined the performance of classical and Bayesian estimators of four effect size measures for the indirect effect in a single-mediator model and a two-mediator model. Compared to the proportion and ratio mediation effect sizes, standardized mediation effect-size measures were relatively unbiased and efficient in the single-mediator model and the two-mediator model. Percentile and bias-corrected bootstrap interval estimates of ab/sY, and ab(sX)/sY in the single-mediator model outperformed interval estimates of the proportion and ratio effect sizes in terms of power, Type I error rate, coverage, imbalance, and interval width. For the two-mediator model, standardized effect-size measures were superior to the proportion and ratio effect-size measures. Furthermore, it was found that Bayesian point and interval summaries of posterior distributions of standardized effect-size measures reduced excessive relative bias for certain parameter combinations. The standardized effect-size measures are the best effect-size measures for quantifying mediated effects.

Original languageEnglish (US)
Pages (from-to)1-17
Number of pages17
JournalBehavior Research Methods
DOIs
StateAccepted/In press - Mar 24 2017

Fingerprint

Mediation
Effect Size
Mediator
Proportion
Bootstrap
Summary

Keywords

  • Bayesian methods
  • Bias
  • Effect sizes
  • Efficiency
  • Interval estimates
  • Mediation

ASJC Scopus subject areas

  • Experimental and Cognitive Psychology
  • Psychology (miscellaneous)
  • Psychology(all)

Cite this

Statistical properties of four effect-size measures for mediation models. / Miočević, Milica; O'Rourke, Holly; Mackinnon, David; Brown, Hendricks C.

In: Behavior Research Methods, 24.03.2017, p. 1-17.

Research output: Contribution to journalArticle

@article{3e10704f99d4485a87f5d6ddab0b3441,
title = "Statistical properties of four effect-size measures for mediation models",
abstract = "This project examined the performance of classical and Bayesian estimators of four effect size measures for the indirect effect in a single-mediator model and a two-mediator model. Compared to the proportion and ratio mediation effect sizes, standardized mediation effect-size measures were relatively unbiased and efficient in the single-mediator model and the two-mediator model. Percentile and bias-corrected bootstrap interval estimates of ab/sY, and ab(sX)/sY in the single-mediator model outperformed interval estimates of the proportion and ratio effect sizes in terms of power, Type I error rate, coverage, imbalance, and interval width. For the two-mediator model, standardized effect-size measures were superior to the proportion and ratio effect-size measures. Furthermore, it was found that Bayesian point and interval summaries of posterior distributions of standardized effect-size measures reduced excessive relative bias for certain parameter combinations. The standardized effect-size measures are the best effect-size measures for quantifying mediated effects.",
keywords = "Bayesian methods, Bias, Effect sizes, Efficiency, Interval estimates, Mediation",
author = "Milica Miočević and Holly O'Rourke and David Mackinnon and Brown, {Hendricks C.}",
year = "2017",
month = "3",
day = "24",
doi = "10.3758/s13428-017-0870-1",
language = "English (US)",
pages = "1--17",
journal = "Behavior Research Methods, Instruments, and Computers",
issn = "1554-351X",
publisher = "Springer New York",

}

TY - JOUR

T1 - Statistical properties of four effect-size measures for mediation models

AU - Miočević, Milica

AU - O'Rourke, Holly

AU - Mackinnon, David

AU - Brown, Hendricks C.

PY - 2017/3/24

Y1 - 2017/3/24

N2 - This project examined the performance of classical and Bayesian estimators of four effect size measures for the indirect effect in a single-mediator model and a two-mediator model. Compared to the proportion and ratio mediation effect sizes, standardized mediation effect-size measures were relatively unbiased and efficient in the single-mediator model and the two-mediator model. Percentile and bias-corrected bootstrap interval estimates of ab/sY, and ab(sX)/sY in the single-mediator model outperformed interval estimates of the proportion and ratio effect sizes in terms of power, Type I error rate, coverage, imbalance, and interval width. For the two-mediator model, standardized effect-size measures were superior to the proportion and ratio effect-size measures. Furthermore, it was found that Bayesian point and interval summaries of posterior distributions of standardized effect-size measures reduced excessive relative bias for certain parameter combinations. The standardized effect-size measures are the best effect-size measures for quantifying mediated effects.

AB - This project examined the performance of classical and Bayesian estimators of four effect size measures for the indirect effect in a single-mediator model and a two-mediator model. Compared to the proportion and ratio mediation effect sizes, standardized mediation effect-size measures were relatively unbiased and efficient in the single-mediator model and the two-mediator model. Percentile and bias-corrected bootstrap interval estimates of ab/sY, and ab(sX)/sY in the single-mediator model outperformed interval estimates of the proportion and ratio effect sizes in terms of power, Type I error rate, coverage, imbalance, and interval width. For the two-mediator model, standardized effect-size measures were superior to the proportion and ratio effect-size measures. Furthermore, it was found that Bayesian point and interval summaries of posterior distributions of standardized effect-size measures reduced excessive relative bias for certain parameter combinations. The standardized effect-size measures are the best effect-size measures for quantifying mediated effects.

KW - Bayesian methods

KW - Bias

KW - Effect sizes

KW - Efficiency

KW - Interval estimates

KW - Mediation

UR - http://www.scopus.com/inward/record.url?scp=85016047465&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016047465&partnerID=8YFLogxK

U2 - 10.3758/s13428-017-0870-1

DO - 10.3758/s13428-017-0870-1

M3 - Article

C2 - 28342072

AN - SCOPUS:85016047465

SP - 1

EP - 17

JO - Behavior Research Methods, Instruments, and Computers

JF - Behavior Research Methods, Instruments, and Computers

SN - 1554-351X

ER -