Interpretation and identification of causal mediation
Open accessThe DOI matches its Crossref record; 88 of the 88 references it cites were found in a registry or an index.
Abstract
This article reviews the foundations of causal mediation analysis and offers a general and transparent account of the conditions necessary for the identification of natural direct and indirect effects, thus facilitating a more informed judgment of the plausibility of these conditions in specific applications. I show that the conditions usually cited in the literature are overly restrictive and can be relaxed substantially without compromising identification. In particular, I show that natural effects can be identified by methods that go beyond standard adjustment for confounders, applicable to observational studies in which treatment assignment remains confounded with the mediator or with the outcome. These identification conditions can be validated algorithmically from the diagrammatic description of one's model and are guaranteed to produce unbiased results whenever the description is correct. The identification conditions can be further relaxed in parametric models, possibly including interactions, and permit one to compare the relative importance of several pathways, mediated by interdependent variables.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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
The central role of the propensity score in observational studies for causal effects
ROSENBAUM, P. R., & RUBIN, D. B. (1983) · Biometrika · doi:10.1093/biomet/70.1.41 · Cited by 31,241
Structural Equations with Latent Variables.
Clogg, C. C., & Bollen, K. A. (1991) · Contemporary Sociology · doi:10.2307/2072165 · Cited by 17,442
Causality: Models, Reasoning, and Inference
Pearl, J. (2009) · doi:10.1017/cbo9780511803161 · Cited by 11,653
Self-citationAddressing Moderated Mediation Hypotheses: Theory, Methods, and Prescriptions
Preacher, K. J., Rucker, D. D., & Hayes, A. F. (2007) · Multivariate Behavioral Research · doi:10.1080/00273170701341316 · Cited by 9,973
Beyond 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 4×
“, Imai, Keele, & Yamamoto, 2010) or uncorrelated error terms. 3 Imai, Keele, and Yamamoto (2010) and Imai, Keele, Tingley, and Yamamoto (2011) discussed similarities and differences among several versions of the identifying assumptions, and Shpitser and VanderWeele (2011) delineated the context under which a restricte…”
InfluentialEstimating causal effects of treatments in randomized and nonrandomized studies
Rubin, D. B. (1974) · Journal of Educational Psychology · doi:10.1037/h0037350 · Cited by 9,436 · cited 2×
“Counterfactual thinking in statistics (Holland, 1988; Rubin, 1974) and epidemiology (Robins and Greenland, 1992), together with a formal semantics based on non-parametric structural equations (Balke and Pearl, 1995; Halpern, 1998; Pearl, 2001) have given causal mediation analysis a sound theoretical basis and have ext…”
Introduction to Statistical Mediation Analysis
MacKinnon, D. P. (2012) · doi:10.4324/9780203809556 · Cited by 5,618
Fisher, R. A. (1936) · BMJ · doi:10.1136/bmj.1.3923.554-a · Cited by 4,980
CAUSALITY: MODELS, REASONING AND INFERENCE
Hitchcock, C. (2001) · The Philosophical Review · doi:10.1215/00318108-110-4-639 · Cited by 4,741
Self-citation
Cited by
Items 301–400 of 554
Invariant graph learning meets information bottleneck for out-of-distribution generalization
Mao, W., Wu, J., Liu, H., Sui, Y., & Wang, X. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-025-40798-3 · Cited by 17
“Poole et al. [45] has expounded upon the intricate interplay between mutual information and its assorted lower bounds, wherein the contrastive loss mechanism emerges as a prevalent methodological choice.”
Decomposition of the total effect for two mediators: A natural mediated interaction effect framework
Gao, X., Li, L., & Luo, L. (2022) · Journal of Causal Inference · doi:10.1515/jci-2020-0017 · Cited by 6
“The seminatural indirect effect through M2, SNIEM2, measures the causal effect along the path A → M2 → Y and can be interpreted as the effect due to partial mediation through M2 only [19,20].”
BackgroundMethodCausal diagrams for civil and structural engineers
Naser, M. Z. (2024) · Structures · doi:10.1016/j.istruc.2024.106398 · Cited by 4
“According to Pearl [34], “..”
A Comparison of Potential Outcome Approaches for Assessing Causal Mediation
Coffman, D. L., MacKinnon, D. P., Zhu, Y., & Ghosh, D. (2016) · ICSA book series in statistics · doi:10.1007/978-3-319-41259-7_14 · Cited by 8
A Causal Power Semantics for Generic Sentences
van Rooij, R., & Schulz, K. (2019) · Topoi · doi:10.1007/s11245-019-09663-4 · Cited by 4
“But a causal analysis can be useful here as well, as shown by the recent abundance of papers on mediation (e.g. Preacher and Kelley 2011; Pearl 2014): causal models can (be used to) explain not only why something happened, but also how it happened.”
BackgroundOakey‐Frost, N., Trachik, B. J., Ganulin, M. L., LoPresti, M. L., Dretsch, M. N., & Tucker, R. P. (2021) · Military Psychology · doi:10.1080/08995605.2021.1902180 · Cited by 8
“Further, beyond the inability to determine causal relationships, mediation analyses are not recommended for convenience sample data like those analyzed in the current study (Pearl, 2014).”
BackgroundTemperament and Brain Networks of Attention
Rothbart, M., Posner, M., & Sheese, B. E. (2020) · The Cambridge Handbook of Personality Psychology · doi:10.1017/9781108264822.016 · Cited by 1
Covenant-lite agreement and credit risk: A key relationship in the leveraged loan market
Novellis, G. D., Tanzi, P. M., & Stanghellini, E. (2024) · Research in International Business and Finance · doi:10.1016/j.ribaf.2024.102377 · Cited by 9
Enduring maternal brain changes and their role in mediating motherhood’s impact on well-being
Rotondi, V., Allegra, M., Kashyap, R., Barban, N., Sironi, M., & Reverberi, C. (2024) · Scientific Reports · doi:10.1038/s41598-024-67316-y · Cited by 10
Luo, C., Wu, X., Wang, W., Zhang, M., Cheng, F., Chen, H., & Tung, T. (2022) · Frontiers in Public Health · doi:10.3389/fpubh.2022.865046 · Cited by 4
“Based on mediation analysis, researchers could easily partition the total effect of an independent variable on an outcome variable into direct and indirect effects via an intermediate variable (17, 18).”
BackgroundCare and anger motives in social dilemmas
Ring, P., Schütt, C. A., & Snower, D. J. (2023) · Theory and Decision · doi:10.1007/s11238-022-09921-9 · Cited by 7
“fi 1⁄4 Yið1;MiðtÞÞ Yið0;MiðtÞÞ ð6Þ for the treatment status t 1⁄4 0; 1 (Pearl, 2014; Robins & Greenland, 1992).”
Evidence Required to Know Whether Marriage Promotion Increases Other Social Benefits
Feld, S. L., & Meyer, J. (2018) · Journal of Family Theory & Review · doi:10.1111/jftr.12297 · Cited by 4
SAS® Macros for Computing the Mediated Effect in the Pretest-Posttest Control Group Design.
Valente, M. J., & MacKinnon, D. P. (2017) · PubMed · Cited by 6
SAS® Macros for Computing Causal Mediated Effects in Two- and Three-Wave Longitudinal Models.
Valente, M. J., & MacKinnon, D. P. (2018) · PubMed · Cited by 5
Biesanz, J. C., & Wallace, J. D. (2020) · The Cambridge Handbook of Personality Psychology · doi:10.1017/9781108264822.006 · Cited by 1
Personality in Clinical Psychology
Widiger, T., & McCabe, G. A. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.042 · Cited by 1
The Effects of Parent Ages on Birth Defects
Thompson, J. A. (2020) · Acta Scientific Paediatrics · doi:10.31080/aspe.2020.03.0312 · Cited by 4
iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with InterpretabilityPreprint
Chadha, A. R., & Jain, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.10300 · Cited by 6
“There has been a recent surge of interest in coupling the complementary strengths of computer vision and causal reasoning [28, 29].”
BackgroundA Distinction between Causal Effects in Structural and Rubin Causal ModelsPreprint
Aliprantis, D. (2015) · SSRN Electronic Journal · doi:10.2139/ssrn.2587076 · Cited by 7
Rigorously assessing natural language explanations of neurons
Huang, J., Geiger, A., D’Oosterlinck, K., Wu, Z., & Potts, C. (2023) · Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/2023.blackboxnlp-1.24 · Cited by 3
Sleep, movement, and dietary behaviours: the mediating role of affect
Zhong, Q., & Huang, J. (2024) · Psychology and Health · doi:10.1080/08870446.2024.2390027 · Cited by 4
“From a conceptual perspective, the direct effect is the expected change in the outcome if we were to ‘freeze’ the mediator value, while the indirect effect is the expected change in the outcome when the mediator changes (Pearl, 2014).”
How do manipulation checks interfere with the inference of causal relationships?
Han, Y., & Lee, W. (2024) · Behavior Research Methods · doi:10.3758/s13428-024-02573-3 · Cited by 6
PFCA: Efficient Path Filtering with Causal Analysis for Healthcare Risk Prediction
Wang, H., Shi, J., Chen, Y., Xu, H., Zhang, C., Luo, Z., & Zhang, M. (2025) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65448.2025.00176 · Cited by 4
Sleep disturbance recorded via wearable sensors predicts depression severity 9 years later
Zainal, N. H., & Hitchcock, P. (2025) · Journal of Affective Disorders · doi:10.1016/j.jad.2025.120426 · Cited by 5
“Participants ( N = 1054) took part in the Midlife Development in the United States (MIDUS) Biomarker project (Love et al., 2010) as well as the MIDUS survey studies at baseline (Wave 1; W1; 2004 to 2006; Ryff et al., 2021) and follow-up (Wave 2; W2; 2013 to 2014; Ryff et al., 2019).”
Nurse Well-being Drives Patient Satisfaction in Magnet Hospitals
Yu, H., Aiken, L. H., Willis, P., Kaplow, R., Pappas, S. H., Burke, D., Ditomassi, M., & Lasater, K. B. (2025) · JONA The Journal of Nursing Administration · doi:10.1097/nna.0000000000001671 · Cited by 6
Teng, Z., & Bushman, B. J. (2025) · Aggressive Behavior · doi:10.1002/ab.70054 · Cited by 4
Narrative Identity in the Social World
McLean, K. C., Syed, M., Haraldsson, K. G., & Lowe, L. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.035
Poor economics and its missing mechanisms: The case for causal mediation
Kumar, S. M., & Venkatachalam, R. (2023) · Review of Development Economics · doi:10.1111/rode.13029 · Cited by 4
“These can be expressed formally as follows, under the additional overall assumption that the data is generated from a Non-Parametric Structural Equation Model (Pearl, 2009, 2014).”
BackgroundCholesterol, Triglyceride, and Glucose Levels Across Birth Cohorts in the US
Huang, X., Petito, L. C., Shah, N. S., Lloyd‐Jones, D. M., Khan, S. S., & Cameron, N. A. (2024) · JAMA Network Open · doi:10.1001/jamanetworkopen.2024.49481 · Cited by 4
Liu, H., Heo, I., Ivanov, A., & Depaoli, S. A. (2025) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2025.2503789 · Cited by 5
“To draw valid causal inferences, it is essential to establish a theoretical basis for the causal pathway from X to M to Y and to consider potential confounders that may influence the relationships among these variables (Imai et al., 2010; Pearl, 2014).”
Salgado, J., Anderson, N., & Moscoso, S. (2020) · The Cambridge Handbook of Personality Psychology · doi:10.1017/9781108264822.040
Sun, R., Jia, J., Wang, S., Wang, Z., Wang, C., Xu, Y., & Yang, Y. (2024) · Endocrine · doi:10.1007/s12020-023-03669-0 · Cited by 3
Siddique, S., Gore, R. J., Zhang, Y., & Punnett, L. (2024) · Journal of Occupational and Environmental Medicine · doi:10.1097/jom.0000000000003063 · Cited by 8
“Exposure-mediator interaction is avalid effect 38,39 that is seldom quantified in mediation analysis 40 but should not be overlooked.”
BackgroundChen, G., Xia, X., Zhang, Y., et al. (2025) · Metabolic Brain Disease · doi:10.1007/s11011-024-01499-1 · Cited by 3
“(Pearl 2014)”
Causal inference model for accurate medical diagnosis in Coronary Artery Bypass Graft operation
Zhang, Q., Zhang, W., Li, Q., Bai, Y., Nie, W., & Xie, K. (2025) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2025.103150 · Cited by 4
Zainal, N. H., & Doren, N. V. (2025) · Journal of Anxiety Disorders · doi:10.1016/j.janxdis.2025.103052 · Cited by 3
“They completed the same structured psychiatric interview at Wave 2 (W2; 2013 – 2014; Ryff et al., 2019a).”
Models of Personality Structure
de Raad, B., & Barelds, D. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.012
Cognitive Processes and Models
Matthews, G. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.028 · Cited by 4
Liu, C., Cao, W., Meng, X., Shen, J., Liang, X. R., Guo, Y., & Tang, K. (2021) · LGBT Health · doi:10.1089/lgbt.2020.0320 · Cited by 3
Srakar, A. (2018) · Croatian International Relations Review · doi:10.2478/cirr-2018-0011 · Cited by 3
“These two considerations lead to the analysis of natural direct and indirect effects (Pearl 2014: 459).”
BackgroundMethodTesting the mediated effect of a model with a binary dependent variable
Kim, S.-B., & Kim, S. (2018) · 한국심리학회지: 일반 · doi:10.22257/kjp.2018.09.37.3.441 · Cited by 3
A More Efficient Causal Mediator Model Without the No-Unmeasured-Confounder Assumption
Brandt, H. (2019) · Multivariate Behavioral Research · doi:10.1080/00273171.2019.1656051 · Cited by 7
Basic Needs, Goals and Motivation
Szalma, J. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.030 · Cited by 4
Personality in Cross-Cultural Perspective
Dragūns, J., & Tanaka-Matsumi, J. (2020) · The Cambridge Handbook of Personality Psychology · doi:10.1017/9781108264822.037 · Cited by 3
Park, S. J., Tafti, A., & Shmueli, G. (2023) · Information Systems Research · doi:10.1287/isre.2023.1236 · Cited by 3
Models of Physical Health and Personality
Heilmayr, D., & Friedman, H. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.019 · Cited by 4
Noncompliance in randomized control trials without exclusion restrictionsPreprint
Sawada, M. (2019) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.1910.03204 · Cited by 7
“2013; Mealli and Pacini, 2013) and mediation analysis literature (Pearl, 2014).”
BackgroundInfluentialMcCormick, E. M., Borgeest, G. S., & Kievit, R. (2022) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/48xj5 · Cited by 3
Loh, W. W., & Ren, D. (2022) · doi:10.31234/osf.io/s387m · Cited by 3
A Semantics for Causing, Enabling, and Preventing Verbs Using Structural Causal ModelsPreprint
Cao, A., Geiger, A., Kreiss, E., Icard, T., & Gerstenberg, T. (2023) · doi:10.31234/osf.io/kpu52 · Cited by 3
Sequential Ignorability and Dismissible Treatment Components to Identify Mediation Effects
Deng, Y., Wei, H., Xiao, X., Zhang, Y., & Huang, Y. (2024) · Mathematics · doi:10.3390/math12152332 · Cited by 4
Chen, L., Zhang, M., Xiang, S., Zhang, J., Chang, R., Hu, C., Qian, S., Liu, T., Shi, Y., & Ding, X. (2025) · Journal of Psychosomatic Research · doi:10.1016/j.jpsychores.2025.112049 · Cited by 2
Unraveling drought propagation dynamics using causal inference from time series
Pang, M., & Yang, S. (2025) · Environmental Research Letters · doi:10.1088/1748-9326/ae151e · Cited by 7
“CE analysis aims to quantify the relative effects of various pathways and interactions within a causal graph, revealing how changes are transmitted from causes to outcomes (Pearl 2014).”
Causal Mediation Analysis in Pregnancy Studies: the Case of Environmental Epigenetics
Valeri, L. (2017) · Current Epidemiology Reports · doi:10.1007/s40471-017-0112-1 · Cited by 2
“2 Department of Psychiatry, Harvard Medical School, Boston, MA 02115, USA Curr Epidemiol Rep (2017) 4:117–123”
BackgroundMethodInfluentialKumar, S. M. (2023) · Springer eBooks · doi:10.1007/978-981-19-4166-5_14 · Cited by 3
Smith, M. L., Gelaye, B., Tsai, A. C., & Gradus, J. L. (2024) · Annals of Epidemiology · doi:10.1016/j.annepidem.2024.02.003 · Cited by 3
Thompson, J. A. (2024) · Journal of Clinical Medicine · doi:10.3390/jcm13123464 · Cited by 3
“The proposed research approach permits the evaluation of multiple interacting mediators.”
BackgroundCROCODILE: Causality Aids RObustness via COntrastive DIsentangled LEarning
Carloni, G., Tsaftaris, S. A., & Colantonio, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73158-7_10 · Cited by 6
Estimating Mediation Effects in ABAB Reversal Designs
Valente, M. J., Pang, J., Rijnhart, J. J. M., Ferron, J. M., & Miočević, M. (2024) · Evaluation & the Health Professions · doi:10.1177/01632787231217000 · Cited by 2
“…related to both the mediator and the outcome because the individual will still “ self-select ” their value of the mediator (Hong, 2015; Imai, Keele, & Tingley, 2010; Imai, Keele, & Yamamoto, 2010; Pearl, 2001, 2014; Valeri & Vanderweele, 2013; VanderWeele, 2015; VanderWeele & Vansteelandt, 2009).”
Mediation Analysis of Serum Fibroblast Growth Factor 20 and Poor Prognosis After Ischemic Stroke
Chen, K., Huang, W., Hu, B., Fu, F., Cao, Y., Xu, H., Ruan, L., Li, Y., Li, Y., Chen, J., et al. (2024) · Journal of the American Heart Association · doi:10.1161/jaha.124.036721 · Cited by 3
“The causal mediation analysis was conducted within the counterfactual framework 25 based on the theories of Baron and Kenny, 26 as well as Valeri and VanderWeele.”
CCLNet: Causal and Contrastive Learning Framework for Enhanced Pulmonary Embolism Detection
Wang, Z., Ge, R., Yu, J., Qin, F., Tian, Y., Li, N., Min, W., Elazab, A., & Wang, C. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10821899 · Cited by 2
Xu, S., Burr, J. A., Song, Q., & Ehrlich, J. R. (2025) · Innovation in Aging · doi:10.1093/geroni/igaf016 · Cited by 2
“…model was interpreted in terms of a linear regression using the latent response formulation (Pratschke et al., 2016), the direct effects in the statistical model are equivalent to “natural direct effects,” while the total effect was given by the sum of the direct and indirect effects (Pearl, 2014).”
Ebasone, P. V., Peer, N., Dzudié, A., Foaleng, M., Melpsa, J., & Kengne, A. P. (2025) · BMC Medical Research Methodology · doi:10.1186/s12874-025-02498-1 · Cited by 4
“This omission is significant because the validity of mediation analysis results heavily depends on these assumptions, such as the assumption of no unmeasured confounding between the mediator and the outcome [16, 18, 23].”
InfluentialCausal Directions Matter: How Environmental Factors Drive Convective Cloud Detrainment Heights
Wang, D., Lee, S. H., Zhang, T., Lackner, C. P., Kirshbaum, D. J., & Jensen, M. P. (2025) · Geophysical Research Letters · doi:10.1029/2025gl114941 · Cited by 2
“Additionally, a spurious causation may be identified if certain confounders are not included (unmeasured or undiscovered) in the analysis (e.g., Pearl, 2014).”
InfluentialThe inflammation-depression link: How social networks buffer or exacerbate risk
Zainal, N. H. (2025) · Brain Behavior & Immunity - Health · doi:10.1016/j.bbih.2025.101052 · Cited by 4
“Second, most studies examining the associations among inflammation, social support, and MDD severity have been cross-sectional (Colasanto et al., 2020; Rueger et al., 2016), limiting the ability to draw weak causal inferences (Pearl, 2014).”
Talaugon, A. R., Turanovic, J. J., & Siennick, S. E. (2025) · Journal of School Violence · doi:10.1080/15388220.2025.2531976 · Cited by 5
“…in the outcome (e.g., suspension) that occurs when holding the independent variable (e.g., victimization) constant, and changing the mediator (e.g., school problem behaviors) from the value under the control condition to the value under the treatment condition (Imai et al., 2010; Pearl, 2014).”
CTEA: Camouflaged topological element attack via causal influence discovery
Jia, J., Gao, P., Luo, M., Wu, C., & Guo, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129160 · Cited by 2
Causal Measures of the Treatment Effect Captured by Candidate Surrogate Endpoints
Kobayashi, F., & Kuroki, M. (2015) · Journal of Agricultural Biological and Environmental Statistics · doi:10.1007/s13253-015-0215-4 · Cited by 2
“2, even if both X and S are randomized (Pearl 2014).”
BackgroundCausal Thinking in the Twilight Zone
Pearl, J. (2015) · Observational Studies · doi:10.1353/obs.2015.0020 · Cited by 2
“…complete solutions6 to several long-standing problem areas, ranging from policy evaluation (Tian and Shpitser, 2010) and selection bias (Bareinboim, Tian and Pearl, 2014) to external validity (Bareinboim and Pearl, 2015; Pearl and Bareinboim, 2014) and missing data (Mohan, Pearl and Tian, 2014).”
BackgroundSelf-citationKeele, L. J., Tingley, D. H., & Yamamoto, T. (2015) · Cited by 2
A causal mediation model of ischemia reperfusion injury in the retina
Soliman, M., Andreeva, K., Nasraoui, O., & Cooper, N. G. F. (2017) · PLoS ONE · doi:10.1371/journal.pone.0187426 · Cited by 2
Mikulincer, M., & Shaver, P. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.020 · Cited by 10
Quantifying causal effects from observed data using quasi-intervention
Yang, J., Wan, Y., Ni, Q., Zuo, J., Wang, J., Zhang, X., & Zhou, L. (2022) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-022-02086-z · Cited by 4
“With the aid of the manipulated graph and the do-algorithm [8, 10, 11, 21], we eliminate the do operation in P(Y |do(X = x)) , which represents hypothetical intervention and cannot be obtained from the dataset.”
MethodHypothesis-driven mediation analysis for compositional data: an application to gut microbiome
Kartiosuo, N., Nevalainen, J., Raitakari, O. T., Pahkala, K., & Auranen, K. J. (2024) · Biostatistics & Epidemiology · doi:10.1080/24709360.2024.2360375 · Cited by 3
“We treat the total, direct and indirect effects of exposure within the potential outcomes framework [8].”
InfluentialLi, Y., Zhang, M., Ke, W., & Li, W. (2025) · Journal of Medical Internet Research · doi:10.2196/72315 · Cited by 3
“…significant flexibility in modeling various types of outcomes, including linear models, probit models, survival analysis models, and others [16,20]; and (4) finally, it incorporates sensitivity analysis to assess the robustness of the sequential ignorability assumption, ensuring the…”
InfluentialA Bayesian finite mixture of bivariate regression model for causal mediation analyses
Lefebvre, G., Samoilenko, M., Boucoiran, I., & Blais, L. (2018) · Statistics in Medicine · doi:10.1002/sim.7835 · Cited by 2
Offsetting Policy Feedback Effects: Evidence from the Affordable Care ActPreprint
Hobbs, W., & Hopkins, D. J. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3366994 · Cited by 2
Basak, E., Tafti, A., & Watson‐Manheim, M. B. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3544999 · Cited by 2
Thrash, T. M., Belzak, W. C. M., Wadsworth, L. M., & Sim, Y. Y. (2020) · Springer eBooks · doi:10.1007/978-3-319-24612-3_1314 · Cited by 4
Interventions in dynamic systems: A causal approach to continuous-time mediation analysisPreprint
Ryan, O. (2018) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/n2fwt · Cited by 2
Structural modelling in policymaking
Attansio, O., & Blair, D. (2018) · doi:10.51744/cip9 · Cited by 3
“15 Judea Pearl (2018) in his recent book discusses the example of the study of Jon Snow who in the nineteenth century was trying to identify the causes of cholera and was relating them to the quality of water.”
BackgroundInfluentialPersonality Traits and Mental Disorders
Hakulinen, C., Jokela, M., Kivimäki, M., & Elovainio, M. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.018 · Cited by 3
Anxiety, Depression and Cognitive Dysfunction
Eysenck, M., & Holmes, A. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.033 · Cited by 3
Lynam, D., Vize, C. E., & Miller, J. D. (2020) · The Cambridge Handbook of Personality Psychology · doi:10.1017/9781108264822.043
RELATIONSHIP BETWEEN SCHOOL CLIMATE AND TEACHER COMMITMENT
Jusoh, M. M., & Ismail, S. N. (2021) · International Journal of Education Psychology and Counseling · doi:10.35631/ijepc.642042 · Cited by 1
Individualized treatment rule characterization via a value function surrogate
Freeman, N. L. B., Browder, S. E., McGinigle, K. L., & Kosorok, M. R. (2024) · Biometrics · doi:10.1093/biomtc/ujad012 · Cited by 5
Spit, S., Andringa, S. J., & Ryan, O. (2025) · Language Learning · doi:10.1111/lang.12713 · Cited by 1
“There may be mediating variables that play different indirect roles in the causal effect of interest (Imai et al., 2010a, 2010b; Pearl, 2014; VanderWeele, 2015), and not all of the relevant variables in the dataset at hand may have been observed.”
Enhancing temporal knowledge graph completion with counterfactual insights
Zhang, Y., Ma, G., Sun, L., Xu, D., Pang, S., & Yang, F. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07579-y · Cited by 1
Crawford, J., Collier, E. S., Gunnarsson, K. U., Shorter, G. W., McCambridge, J., Lundgren, O., & Bendtsen, M. (2025) · BMJ Open · doi:10.1136/bmjopen-2025-100532 · Cited by 2
“75 Medi-ated effects will be studied contrasting the intervention groups against each other and against the control group.”
Accountability, Involvement, and Mediation for Information Flow
Kozyri, E., Schneider, F. B., & Chong, S. (2025) · Proceedings - Computer Security Foundations Workshop/Proceedings · doi:10.1109/csf64896.2025.00013 · Cited by 1
“Pear [23] does not identify variables that are interconnected with non-correlative relations, whereas CD-trajectories do identify these variables.”
Yang, S., Ren, J., Li, J., & Zhang, D. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112595 · Cited by 1
How Organizational Inclusion Shapes Patient Satisfaction in Magnet Hospitals
Yu, H., Brom, H. M., Bauermeister, J. A., Reich, J. A., McHugh, M. D., Hanneman, T., & Aiken, L. H. (2025) · Medical Care · doi:10.1097/mlr.0000000000002201 · Cited by 3
Lv, P., Wang, Y., Liu, M., Zhang, Z., Ma, Y., Liu, L., & Meijering, E. H. W. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3620585 · Cited by 11
Phillips, D. E., Thomas, J.-T., & Ikilezi, G. (2025) · Vaccines · doi:10.3390/vaccines13111136 · Cited by 2
“Use of the term “decomposition analysis” subtly varies within the literature as well; at times it is used in reference to separating direct and indirect effects, and at other times it is used in reference to data that are compositional [29,36].”
Tovar‐García, E. D. (2025) · International Journal of Sport Finance · doi:10.1177/15586235251394463 · Cited by 1
“In addition, other empirical strategies for mediation analysis should be explored (Pearl, 2014).”
Loeys, T., Poppe, L., Dierckens, M., & Moerkerke, B. (2025) · Journal of Behavioral Medicine · doi:10.1007/s10865-025-00615-5 · Cited by 2
“Natural effects require the following additional identifi - cation assumptions (Imai et al., 2010a; Pearl, 2014”
Cui, F., Wang, M., Tang, L., Ma, Y., Wang, J., Zheng, L., Xing, M., Xie, J., Han, L., & Tian, Y. (2026) · Journal of Advanced Research · doi:10.1016/j.jare.2026.01.043 · Cited by 1
Iqbal, J., Moineddin, R., Fowler, R. A., Krzyzanowska, M. K., Booth, C. M., Earle, C., Lau, J., Le, L. W., Carpén, T. P., Downar, J., et al. (2026) · EClinicalMedicine · doi:10.1016/j.eclinm.2026.103759 · Cited by 3
Metadata
- Authors
- Pearl, J.
- Affiliations
- University of California, Los Angeles (US)
- Corresponding author
- Pearl, Judea
- Venue
- Psychological Methods
- Published
- 2014
- Volume
- 19
- Issue
- 4
- Pages
- 459-481
- ISSN
- 1082-989X (ISSN-L)
- 1939-1463
- OpenAlex
- W1967742189
- Cited by
- 554
- References
- 84
- Citations by year
- 2026: 45 · 2025: 52 · 2024: 49 · 2023: 49 · 2022: 56 · 2021: 57 · 2020: 87 · 2019: 38 · 2018: 32 · 2017: 33 · 2016: 25 · 2015: 21 · 2014: 10
- FWCI
- 31.34
- Type
- journal article
- Language
- en
- Open access
- green
- autopapers.ssrn.com
- Locations
- Psychological Methods (publishedVersion)
- PubMed (publishedVersion)
- SSRN Electronic Journal (submittedVersion)
- Funders
- National Institutes of Health (1R01 LM009961-01)
- National Science Foundation (IIS-0914211 and IIS-1018922)
- Office of Naval Research (N000-14-09-1-0665 and N00014-10-1-0933)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Philosophy of Biology and Scientific Explanation
- Keywords
- causal mediation analysis, natural direct and indirect effects, identifiability conditions, observational studies, confounding, parametric models, interaction, probabilistic graphical models
- MeSH terms
- Humans, Statistics as Topic, Models, Statistical, Causality
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.