Power Anomalies in Testing Mediation
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Two rather surprising anomalies relating to statistical power occur in testing mediation. First, in a model with no direct effect for which the total effect and indirect effect are identical, the power for the test of the total effect can be dramatically smaller than the power for the test of the indirect effect. Second, when there is a direct effect of a causal variable on the outcome controlling for the mediator, the power of the test of the indirect effect is often considerably greater than the power of the test of the direct effect, even when the two are of the same magnitude. We try to explain the reasons for these anomalies and how they affect practice.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Kenny and Judd (2014) recently demonstrated that the power of the test of the indirect effect in mediational models is often considerably greater than the test of the direct effect.”
From Nostalgia-Evoked Inspiration: Mediating Mechanisms and Motivational Implications (2015) · cites this paper as Kenny and Judd (2014)
In the citing paper
“Indeed, Kenny and Judd (2014) noted that in the absence of a DE, testing the IE in a mediation analysis can be dramatically more powerful than the standard method testing SNP-disease associations directly.”
From Integrative Analysis of Multi-omics Data for Discovery and Functional Studies of Complex Human Diseases (2016) · cites this paper as Kenny and Judd (2014)
Citations
Cites
Baron, R. M., & Kenny, D. A. (1986) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.51.6.1173 · Cited by 91,532
Self-citationMediation 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 2×
“Shrout and Bolger (2002) explicitly acknowledged the low power in the test of the total effect.”
BackgroundResultBeyond Baron and Kenny: Statistical Mediation Analysis in the New Millennium
Hayes, A. F. (2009) · Communication Monographs · doi:10.1080/03637750903310360 · Cited by 9,757 · cited 3×
“We shall see that this strategy for claiming complete mediation is often inadvisable, a point raised previously by several investigators (Hayes, 2009; Preacher & Kelley, 2011; Rucker et al., 2011).”
BackgroundResultA comparison of methods to test mediation and other intervening variable effects
MacKinnon, D. P., Lockwood, C. M., Hoffman, J. M., West, S. G., & Sheets, V. (2002) · Psychological Methods · doi:10.1037/1082-989x.7.1.83 · Cited by 9,406 · cited 2×
“The finding that c has relatively low power, relative to the test of the indirect effect was perhaps first noted by MacKinnon et al. (2002).”
MethodResultRequired sample size to detect the mediated effect
Fritz, M. S., & MacKinnon, D. P. (2007) · Psychological Science · doi:10.1111/j.1467-9280.2007.01882.x · Cited by 4,810
Preacher, K. J., & Kelley, K. (2011) · Psychological Methods · doi:10.1037/a0022658 · Cited by 3,060 · cited 2×
“We shall see that this strategy for claiming complete mediation is often inadvisable, a point raised previously by several investigators (Hayes, 2009; Preacher & Kelley, 2011; Rucker et al., 2011).”
BackgroundResultProcess Analysis: Estimating Mediation in Treatment Evaluations
Judd, C. M., & Kenny, D. A. (1981) · Evaluation Review · doi:10.1177/0193841x8100500502 · Cited by 2,442 · cited 1×
“The violation of these assumptions can lead to seriously mistaken conclusions (Bullock, Green, & Ha, 2010; Judd & Kenny, 1981, 2010).”
BackgroundSelf-citationMediation Analysis in Social Psychology: Current Practices and New Recommendations
Rucker, D. D., Preacher, K. J., Tormala, Z. L., & Petty, R. E. (2011) · Social and Personality Psychology Compass · doi:10.1111/j.1751-9004.2011.00355.x · Cited by 2,430 · cited 3×
“We shall see that this strategy for claiming complete mediation is often inadvisable, a point raised previously by several investigators (Hayes, 2009; Preacher & Kelley, 2011; Rucker et al., 2011).”
BackgroundResultHayes, A. F., & Scharkow, M. (2013) · Psychological Science · doi:10.1177/0956797613480187 · Cited by 2,387 · cited 2×
“When there are discussions of statistical power, they are mostly focused on the power of the overall test of mediation (Fritz & MacKinnon, 2007; Hayes & Scharkow, 2013; MacKinnon, Lockwood, Hoffman, West, & Sheets, 2002).”
BackgroundMethodStatistical Strategies for Small Sample Research
Hoyle, R. H. (1999) · Cited by 2,116
Cited by
Items 501–536 of 536
Sharma, Y., Castellanos, J., Suero-Tejeda, N. M., Bockting, W. O., Kronish, I. M., Schwartz, J. E., Wall, M. M., & Caceres, B. A. (2025) · BMC Public Health · doi:10.1186/s12889-025-24061-9
“We will conduct mediation analyses regardless of finding significant associations in Hypothesis 1a because of the likely greater power to detect mediation than the total effects of anticipated and vicarious discrimination on home SBP [94].”
Ferdy, Kaihatu, T. S., & Sutrisno, T. F. (2025) · International Journal of Accounting and Economics Studies · doi:10.14419/j0yy3w86
Pilato, J., Cortes, R. A., Peterson, E. G., Uttal, D. H., Kolvoord, R. A., & Green, A. E. (2025) · Scientific Reports · doi:10.1038/s41598-025-29345-z
“…often has a reduced focus on the causal steps approach to mediation, which past work has proposed can be beneficial 69 are present in mediation analyses, the direct effect can be underpowered to detect a significant effect when the mediated effect is not due to variations in standard error 70 .”
Venkat, R., & Carter-Rogers, K. (2026) · Current Psychology · doi:10.1007/s12144-025-08698-8
“While there has been some discussion within literature pertaining to the indirect effect meaning there could be a mediation, but the direct effect lacks power, Kenny and Judd (2014) warn caution must be taken when substituting the test of the indirect effect for the total effect.”
Yujiao, M., Mahadi, B., & Toh, S. M. (2026) · European Journal of Sustainable Development · doi:10.14207/ejsd.2026.v15n1p865
“According to the guidance of Kenny and Judd (2014), even relatively small effect sizes can be considered practically meaningful.”
Watson, H. (2024) · TSpace (University of Toronto)
SAĞLIK İLETİŞİMİ SORUNLARININ HEKİM ALGISINA YANSIMASINDA SİSTEM GÜVENSİZLİĞİNİN ARACI ROLÜ
Yalçın, B. (2026) · Hacettepe sağlık idaresi dergisi · doi:10.61859/hacettepesid.1740252
Santistevan, A. C., Natraj, N., Yack, L. M., Felmingham, K. L., Woodward, S., Mathalon, D. H., Neylan, T. C., & Richards, A. L. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.27.714805
“That said, it has been shown that under certain circumstances tests for mediated effects can have substantially higher power than tests for total effects (Kenny & Judd, 2014) which may be why we observed the significant mediation in the absence of a total effect.”
Epidemiological Study of Diet, Obesity and Asthma in the French EGEA Study
Li, Z. (2017) · theses.fr (ABES) · doi:10.70675/4fe7e0cdza9f9z43f7zb3e8zd3038c3027c2
Bourdier, L. (2017) · theses.fr (ABES) · doi:10.70675/10c7efd8z8329z47e6za285z2d81e7747784 · Cited by 11
Co-opétition et performance créative dans le crowdsourcing d'idées
Elmoukhliss, M.-A. (2018) · theses.fr (ABES) · doi:10.70675/59a81cf1z908dz4f94z81ffz23105ad0051a · Cited by 6
Innovation strategy in developing countries : The case of Vietnamese Small and Medium enterprises
Le, T. K. S. (2018) · theses.fr (ABES) · doi:10.70675/8c81ed24z0108z467dz86c0z3cb02a2004ee
Mohtar, S. I., & Ghalayini, L. K. (2026) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-031-98211-8_4
Phalen, H. J., Gittings, K. L., Adamoli, M. M., Nadler, J., & Salerno, J. M. (2026) · Personality and Social Psychology Bulletin · doi:10.1177/01461672261437443
Qiao, K., Zang, Z., Wang, Y., Chen, X., Liu, K., Zhang, Z., Liu, R., Li, D., Luo, Y., Xiao, L., et al. (2026) · Depression and Anxiety · doi:10.1155/da/9924894
Zhao, P., Zou, J., Li, Y., Liu, S., Zhao, Z. H., & Huang, X. (2026) · Hepatology International · doi:10.1007/s12072-026-11101-8
“Although the total effect of BMI on hepatic steatosis was not statistically significant, mediation analysis can still be conducted to examine the indirect effect [34, 35].”
Psychophysiological Model of Challenge and Threat in Esports
Behnke, M. (2020) · Repozytorium Uniwersytetu im. Adama Mickiewicza (Adam Mickiewicz University in Poznań)
Digital Finance, Entrepreneurship, and Poverty in Africa
Konadu-Yiadom, E., Domeher, D., Appiah, K. O., & Frimpong, J. M. (2026) · Journal of Global Information Technology Management · doi:10.1080/1097198x.2026.2690896
“O’Rourke and MacKinnon (2018) and Kenny and Judd (2014) revealed that significant indirect effects may frequently be found even when the total effect is not statistically significant, supporting the argument made by Zhao et al. (2010).”
Who Gets the Floor? Gender Differences in Speaking, Influence, and Egalitarian Preferences in Groups
Drisdelle, E. (2026) · YorkSpace (York University)
Berny, L. M., Hennessy, E. A., Finch, A. J., & Tanner‐Smith, E. E. (2026) · Drug and Alcohol Dependence · doi:10.1016/j.drugalcdep.2026.113240
Jandré, J. V. R. (2026) · Research Publications (Maastricht University) · doi:10.26481/dis.20260707jr
Vermeulen, G. T., Scherder, E., & Oosterlaan, J. (2026) · International Journal of Sport and Exercise Psychology · doi:10.1080/1612197x.2026.2701834
Suryana, Y., & Hayati, N. R. (2026) · Jurnal Ekonomi Manajemen Sistem Informasi · doi:10.38035/jemsi.v7i6.9264
Nikitina, L., Yuan, F., & Furuoka, F. (2026) · SAGE Open · doi:10.1177/21582440261486108
Poor, S. V., & Herman, B. C. (2026) · Science & Education · doi:10.1007/s11191-026-00779-9
Fernández, M. B., & Ruiz, F. O. (2026) · Journal of Gerontological Social Work · doi:10.1080/01634372.2026.2729364
Umar, A. (2025) · KASU Journal of Management Sciences · doi:10.68022/kjms.2025.c6gq2us5
Susman, E. S., Chen, S., Keltner, D. J., & Harvey, A. G. (2026) · Scientific Reports · doi:10.1038/s41598-026-63457-4
“However, it’s also possible that the study had sufficient power to detect the indirect pathway but not a small direct effect 44 .”
Gong, Q. (2024) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)
Zaji, A., & Bonakdari, H. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7641820
Zaji, A. H., & Bonakdari, H. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7656293
Vorauer, J. D., Bretecher, C., Klassen, C., & Kowalchuk, M. (2026) · Group Processes & Intergroup Relations · doi:10.1177/13684302261494505 · Cited by 1
Support, social impact scaling, and resilience: evidence from minority entrepreneurs
Javadian, G., Mathis, C., Anthony, E. L., Graham, J., & Osorio, A. E. (2026) · Management Decision · doi:10.1108/md-05-2025-1189
Устойчивость сотрудников в организационном контексте во времена турбулентности
Ивановна, К. В., Владимировна, М. О., & Михайловна, Ч. Л. (2026) · Организационная психология
Piyanontalee, R., Feng, J. (., Jayasinghe, M. M., & Gerhart, B. A. (2026) · Human Resource Management Review · doi:10.1016/j.hrmr.2026.101184
Adverse life experiences, mood symptoms, and quality of life in adults with down syndrome
Jenkins, M. R., Hickey, E., Greenlee, J. L., Brothers, C. E., Yoon, D. M., Barry, A. M., Schworer, E. K., Handen, B. L., Hom, C. L., Bodde, A. E., et al. (2026) · Quality of Life Research · doi:10.1007/s11136-026-04439-x
Metadata
- Authors
- Kenny, D. A., & Judd, C. M.
- Affiliations
- University of Connecticut (US)
- University of Colorado Boulder (US)
- Venue
- Psychological Science
- Publisher
- SAGE Publications
- Published
- 2013-12-05
- Volume
- 25
- Issue
- 2
- Pages
- 334-339
- ISSN
- 0956-7976 (ISSN-L)
- 1467-9280
- OpenAlex
- W2131185010
- Cited by
- 497
- References
- 14
- Citations by year
- 2026: 29 · 2025: 35 · 2024: 33 · 2023: 45 · 2022: 40 · 2021: 50 · 2020: 55 · 2019: 49 · 2018: 34 · 2017: 58 · 2016: 29 · 2015: 26 · 2014: 13 · 2013: 1
- FWCI
- 20.34
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
- Locations
- Psychological Science (publishedVersion)
- PubMed (publishedVersion)
- 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
- mediation analysis, statistical power, indirect effects, direct effect, total effect, causal inference
- MeSH terms
- Data Interpretation, Statistical, Humans, Models, Statistical
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
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.