Statistical properties of four effect-size measures for mediation models
Open accessThe DOI matches its Crossref record; 52 of the 55 references it cites were found in a registry or an index.
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/s Y , and ab(s X )/s Y 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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“In addition, a variety of other papers recommend means to improve mediational models, including how to calculate effect sizes (Lachowicz et al., 2018;Miočević et al., 2018) that can facilitate a move away from a focus on null effect significance testing (Götz et al., 2021) and recommendations for best practices (e.g., Fairchild & McDaniel, 2017;Jose, 2019).”
From Acceptance and Commitment Therapy Processes and Mediation: Challenges and How to Address Them (2023) · cites this paper as Miočević et al., 2018
The cited source says what the claim attributes to it.
In the citing paper
“Standardized effect sizes were reported as these may have less bias than proportion- and ratio-based methods (Miočević et al., 2018).”
From The relationship between distress tolerance and behavioral activation on anxiety and depression symptomatology in autistic youth: Leveraging self and caregiver perspectives (2024) · cites this paper as Miočević et al., 2018
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Statistical power analysis for the behavioral sciences
(1990) · Computers, Environment and Urban Systems · doi:10.1016/0198-9715(90)90050-4 · Cited by 65,269
Gelman, A., Carlin, J. B., Stern, H. S., & Rubin, D. B. (2003) · doi:10.1201/9780429258480 · Cited by 27,276
Mediation in experimental and nonexperimental studies: New procedures and recommendations.
Shrout, P. E., & Bolger, N. (2002) · Psychological Methods · doi:10.1037/1082-989x.7.4.422 · Cited by 11,335 · cited 1×
“One common non-parametric alternative to normal theory is the bootstrap (Manly, 1997; MacKinnon, Lockwood, & Williams, 2004; MacKinnon, 2008; Shrout & Bolger, 2002).”
BackgroundIntroduction to Statistical Mediation Analysis
MacKinnon, D. P. (2012) · doi:10.4324/9780203809556 · Cited by 5,618 · cited 12×
“…of Psychology, Arizona State University, 950 S. McAllister Ave, Tempe, AZ 85287, USA 2 Feinberg School of Medicine, Northwestern University, Chicago, IL, USA Y ¼ i2 þ c0Xþ bMþ e2 ð2Þ M ¼ i3 þ aXþ e3 ð3Þ and estimated using only equations 2 and 3, or only equations 1 and 3 (MacKinnon, 2008).”
BackgroundMethodInfluentialSelf-citationRandomization, Bootstrap and Monte Carlo Methods in Biology
Manly, B. F. J. (2018) · Chapman & Hall/CRC eBooks · doi:10.1201/9781315273075 · Cited by 4,194
Preacher, K. J., & Kelley, K. (2011) · Psychological Methods · doi:10.1037/a0022658 · Cited by 3,060 · cited 4×
“Recently, effect-size measures have been proposed that quantify the maximum possible mediation effect that could have been achieved given the constraints of the data and the proportion of that maximum effect that was obtained in a given study (Preacher & Kelley, 2011).”
BackgroundMethodInfluentialStatistical methods in psychology journals: Guidelines and explanations.
Wilkinson, L., & Task Force on Statistical Inference (1999) · American Psychologist · doi:10.1037/0003-066x.54.8.594 · Cited by 2,791
Randomization, Bootstrap and Monte Carlo Methods in Biology.
Kemp, A. W., & Manly, B. F. J. (1997) · Biometrics · doi:10.2307/2533527 · Cited by 1,927 · cited 3×
“The upper confidence limit for the estimate is the value that exceeds a proportion φ(2z0 + z1 −α/2) in that same distribution (Manly, 1997).”
BackgroundA Simulation Study of Mediated Effect Measures
MacKinnon, D. P., Warsi, G., & Dwyer, J. H. (1995) · Multivariate Behavioral Research · doi:10.1207/s15327906mbr3001_3 · Cited by 1,719
Self-citationStice, E. (2001) · Journal of Abnormal Psychology · doi:10.1037/0021-843x.110.1.124 · Cited by 1,251 · cited 1×
“…Ilies & Judge, 2003; Ilies & Judge, 2005; Leigh, 1983; MacKinnon, Johnson, Pentz, Dwyer, Hansen, Flay, & Wang, 1991; Sharkansky, King, King, Wolfe, Erickson, & Stokes, 2000; Stice, 2001; Tein, Sandler, Ayers, & Wolchik, 2006; Wolchik, West, Westover, Sandler, Martin, Lustig, Tein, & Fisher, 1993).”
Research works printed but not linked: 4
- Hayes, A. (2013). Miscellaneous Topics in Mediation Analysis. In Mediation, Moderation, and Conditional Process Analysis (pp. 184–193). New York: Guilford Press.
- Miočević, M., & MacKinnon, D. P. (2014). SAS® for Bayesian Mediation Analysis. In Proceedings of the SAS Global Forum 2014 Conference, Cary NC: SAS Institute Inc.
- Miočević, M., MacKinnon, D. P., & Levy, R. (2016). Comparison of Bayesian and frequentist estimates of the mediated effect. Manuscript under review.
- Taborga, M. P. (2000). Effect size in mediation models. Unpublished master’s thesis, Arizona State University, Tempe, Arizona.
Cited by
Lee, H., Cashin, A. G., Lamb, S. E., Hopewell, S., Vansteelandt, S., VanderWeele, T. J., MacKinnon, D. P., Mansell, G., Collins, G. S., Golub, R. M., et al. (2021) · JAMA · doi:10.1001/jama.2021.14075 · Cited by 548
Self-citationThe structure and predictive value of intrinsic capacity in a longitudinal study of ageing
Beard, J. R., Jotheeswaran, A. T., Cesari, M., & Araujo de Carvalho, I. (2019) · BMJ Open · doi:10.1136/bmjopen-2018-026119 · Cited by 400
Mediation analysis methods used in observational research: a scoping review and recommendations
Rijnhart, J. J. M., Lamp, S. J., Valente, M. J., MacKinnon, D. P., Twisk, J. W. R., & Heymans, M. W. (2021) · BMC Medical Research Methodology · doi:10.1186/s12874-021-01426-3 · Cited by 345
“However, when the indirect effect is estimated based on variables without a naturally meaningful interpretation, such as variables measured on a Likert scale, researchers may alternatively determine the relative effect size by comparing the standardized indirect effect estimate to Cohen’s d [89, 90].”
MethodSelf-citationMeaningful Mediation Analysis: Plausible Causal Inference and Informative Communication
Pieters, R. (2017) · Journal of Consumer Research · doi:10.1093/jcr/ucx081 · Cited by 266
“Various resources for such analyses are available (Fritz and MacKinnon 2007; Gelman and Carlin 2014; Muthén et al. 2016).”
BackgroundMethodInfluentialWang, Y., Tian, L., & Scott Huebner, E. (2019) · Contemporary Educational Psychology · doi:10.1016/j.cedpsych.2019.01.003 · Cited by 159
Metadata
- Authors
- Miočević, M., O’Rourke, H. P., MacKinnon, D. P., & Brown, H. C.
- Affiliations
- Arizona State University (US)
- Northwestern University (US)
- Corresponding author
- Miočević, Milica
- Venue
- Behavior Research Methods
- Published
- 2017-03-24
- Volume
- 50
- Issue
- 1
- Pages
- 285-301
- ISSN
- 1554-351X (ISSN-L)
- 1554-3528
- PMC
- PMC5809552
- OpenAlex
- W2601251367
- Cited by
- 200
- References
- 55
- Citations by year
- 2026: 16 · 2025: 22 · 2024: 24 · 2023: 27 · 2022: 34 · 2021: 28 · 2020: 16 · 2019: 22 · 2018: 10 · 2017: 1
- FWCI
- 9.32
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Behavior Research Methods (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Utrecht University Repository (Utrecht University) (submittedVersion, other-oa)
- eScholarship@McGill (McGill) (submittedVersion)
- Funders
- Utrecht University
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Keywords
- effect size measures, mediation analysis, indirect effects, bootstrap confidence intervals, Bayesian estimation, relative bias, statistical power, type I error rate
- MeSH terms
- Bayes Theorem, Computer Simulation, Humans, Models, Statistical, Bias, Negotiating, Sample Size
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Statistical properties of four effect-size measures for mediation models. https://app.cochat.ai/papers/10.3758/s13428-017-0870-1
- The paper
- Miočević, M., O’Rourke, H. P., MacKinnon, D. P., & Brown, H. C. (2018). Statistical properties of four effect-size measures for mediation models. Behavior Research Methods. https://doi.org/10.3758/s13428-017-0870-1
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.