Causal inference in statistics: An overview
Open accessThe DOI matches its Crossref record; 136 of the 136 references it cites were found in a registry or an index; 2 of the 72 sources its claims cite were checked for support.
Abstract
This review presents empirical researchers with recent advances in causal inference, and stresses the paradigmatic shifts that must be undertaken in moving from traditional statistical analysis to causal analysis of multivariate data. Special emphasis is placed on the assumptions that underly all causal inferences, the languages used in formulating those assumptions, the conditional nature of all causal and counterfactual claims, and the methods that have been developed for the assessment of such claims. These advances are illustrated using a general theory of causation based on the Structural Causal Model (SCM) described in Pearl (2000a), which subsumes and unifies other approaches to causation, and provides a coherent mathematical foundation for the analysis of causes and counterfactuals. In particular, the paper surveys the development of mathematical tools for inferring (from a combination of data and assumptions) answers to three types of causal queries: (1) queries about the effects of potential interventions, (also called “causal effects” or “policy evaluation”) (2) queries about probabilities of counterfactuals, (including assessment of “regret,” “attribution” or “causes of effects”) and (3) queries about direct and indirect effects (also known as “mediation”). Finally, the paper defines the formal and conceptual relationships between the structural and potential-outcome frameworks and presents tools for a symbiotic analysis that uses the strong features of both.
Overview
CoChat Summary
TL;DR
This survey argues that causal inference requires more than standard statistical association: it needs a formal language for causal assumptions and a mathematical machinery for combining those assumptions with data. Pearl presents the Structural Causal Model as a unifying framework that subsumes graphical, potential-outcome, and structural-equation approaches.
Key findings
- The paper distinguishes associational concepts (e.g., correlation, regression, conditional independence) from causal concepts (e.g., intervention, effect, confounding, attribution), arguing that causal claims cannot be defined from observed distributions alone.
- In Markovian structural models, the post-intervention distribution is identified by truncated factorization; for example, the paper shows that \(E(Y \mid do(x_0)) = E(Y \mid X=x_0)\) under the stated assumptions.
- The back-door criterion provides a graphical rule for choosing admissible adjustment sets; the paper states that if a set \(S\) blocks all back-door paths from \(X\) to \(Y\), then stratifying on \(S\) removes confounding bias.
- For noncompliance in clinical trials, the paper says treatment effects are generally nonidentifiable, but bounds can be derived; Balke and Pearl (1997) obtained closed-form bounds for 16 equivalent classes in the binary case, and the paper notes that these bounds can yield “significant and sometimes accurate” information.
Methods
- This is a conceptual review/survey, not an empirical study; it synthesizes advances in causal analysis “from the unifying perspective” of the Structural Causal Model.
- It develops the formalism using structural equations, causal diagrams, do-operator interventions, and counterfactual notation, and then maps these ideas to the potential-outcome framework.
- The analysis is mainly theoretical and illustrative, using examples such as mediation, instrumental variables, covariate adjustment/back-door identification, and noncompliance in clinical trials.
Limitations
- The paper states that counterfactual probabilities conditioned on outcomes “can in general [not] be identified from observational or even experimental studies” without additional conditions.
- It states that natural direct effects “cannot in general be identified or estimated, even with the help of ideal, controlled experiments” unless extra assumptions hold.
- Evident from the text: this is a survey and framework paper, so it does not report a new dataset, sample size, or empirical effect estimate.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
2 Valid · 1 Not valid · 53 Not checked · 133 Own results and interpretations
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Note also that the truncated factorization formula is not restricted to interventions on a single variable; it is applicable to simultaneous or sequential interventions such as those invoked in the analysis of time varying treatment with time varying confounders (Robins, 1986; Arjas and Parner, 2004).”
What the sources say
- Supportedcites Robins, 1986 source
Section F describes treatments assigned at successive times, with assignment depending on past measured covariates. The G-Computation Algorithm multiplies conditional probabilities along treatment and covariate-history paths and sums across those paths to calculate outcomes under a hypothetical treatment. This supports the cited point that the calculation extends beyond an intervention on one variable, although the paper calls it the G-computation algorithm rather than the truncated factorization formula. (LLM, conf=0.87)
- Not checked — no full text of the sourcecites Arjas and Parner, 2004 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“The selection criterion can be applied systematically to diagrams of any size and shape, thus freeing analysts from judging whether ' X is conditionally ignorable given S ,' a formidable mental task required in the potential-response framework (Rosenbaum and Rubin, 1983).”
What the sources say
- Supportedcites Rosenbaum and Rubin, 1983 source
The citation supports the sentence’s reference to conditional ignorability in the potential-response framework. Section 1-2 defines strongly ignorable treatment assignment using the independence of treatment assignment from potential responses given covariates. The diagrammatic selection criterion is the citing authors’ own contrast, not a method attributed to Rosenbaum and Rubin. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A few but challenging algebraic steps would reveal that one can perform the summation over Z 2 to obtain”
- Also stated in: § 3.3. Coping with unmeasured confounders · plain
“which means that we need only adjust for Z 1 and Z 3 without ever measuring Z 2 .”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 3.3. Coping with unmeasured confounders · plain
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The set { Z 3 } , however, is not sufficient for adjustment because, as explained above, it does not block the path X ← W 1 ← Z 1 → Z 3 ← Z 2 → W 2 → Y .”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“This expression coincides with Robins' (1987) G -computation formula, which was derived from a more complicated set of (counterfactual) assumptions.”
What the sources say
- Not checked — no full text of the sourcecites Robins, 1987 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
114 more claims
Create a free account to see all 189 claims and to verify the 7 references still open.
- Probably not a substantial claim. 39
- It may state two separate claims as one. 39
- The quote only partly states this claim. 1
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
“which is known as the truncated factorization formula , see for example, Corollary 1 in Pearl (2009).”
From Discrimination-Free Insurance Pricing (2022) · cites this paper as Pearl (2009)
In the citing paper
““observational data” (such as rfMRI) is in general not a robust and safe tool for inferring causality, compared with “interventional” studies (such as task-fMRI experiments) [63].”
From Functional connectomics from resting-state fMRI (2013) · cites this paper as [63]
Citations
Cites
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 · cited 3×
“The selection criterion can be applied systematically to diagrams of any size and shape, thus freeing analysts from judging whether “X is conditionally ignorable given S,” a formidable mental task required in the potential-response framework (Rosenbaum and Rubin, 1983).”
BackgroundMethod(2001) · RePEc: Research Papers in Economics · Cited by 27,577
Structural Equations with Latent Variables.
Clogg, C. C., & Bollen, K. A. (1991) · Contemporary Sociology · doi:10.2307/2072165 · Cited by 17,442
Structural Equations with Latent Variables
Bollen, K. A. (1989) · Wiley series in probability and statistics · doi:10.1002/9781118619179 · Cited by 17,277 · cited 3×
“…identification has received considerable attention in econometrics (Hurwicz, 1950; Marschak, 1950; Koopmans, 1953) and social science (Duncan, 1975; Bollen, 1989), usually in linear parametric settings, were it reduces to asking whether some model parameter, β, has a unique solution in terms of…”
Causality: Models, Reasoning, and Inference
Pearl, J. (2009) · doi:10.1017/cbo9780511803161 · Cited by 11,653
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×
“…) = ∑ z E(Y |x, z)[P (z|x′)− P (z|x)] (52) This expression deserves the label Mediation Formula, due to its pivotal role in mediation analysis (Imai et al., 2008), which has been a thorny issue in several sciences (Shrout and Bolger, 2002; MacKinnon et al., 2007; Mortensen et al., 2009).”
BackgroundEstimating 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 4×
“…equation models (SEM) used in economics and social science (Goldberger, 1973; Duncan, 1975), the potentialoutcome framework of Neyman (1923) and Rubin (1974), and the graphical models developed for probabilistic reasoning and causal analysis (Pearl, 1988; Lauritzen, 1996; Spirtes et al., 2000;…”
BackgroundMethodInfluentialMacKinnon, D. P., Fairchild, A. J., & Fritz, M. S. (2007) · Annual Review of Psychology · doi:10.1146/annurev.psych.58.110405.085542 · Cited by 5,688 · cited 2×
“…) = ∑ z E(Y |x, z)[P (z|x′)− P (z|x)] (52) This expression deserves the label Mediation Formula, due to its pivotal role in mediation analysis (Imai et al., 2008), which has been a thorny issue in several sciences (Shrout and Bolger, 2002; MacKinnon et al., 2007; Mortensen et al., 2009).”
BackgroundDiscrete Multivariate Analysis: Theory and Practice.
Beniger, J. R., Bishop, Y. M. M., Feinberg, S. E., Holland, P. W., Light, R. J., & Mosteller, F. (1975) · Contemporary Sociology · doi:10.2307/2063625 · Cited by 5,108
Recent Developments in the Econometrics of Program Evaluation
Imbens, G. W., & Wooldridge, J. M. (2009) · Journal of Economic Literature · doi:10.1257/jel.47.1.5 · Cited by 4,926
Research works printed but not linked: 11
- Glymour, M. and Greenland, S. (2008). Causal diagrams. In, Modern Epidemiology (K. Rothman, S. Greenland and T. Lash, eds.), 3rd ed. Lippincott Williams & Wilkins, Philadelphia, PA, 183–209.
- Hurwicz, L. (1950). Generalization of the concept of identification. In, Statistical Inference in Dynamic Economic Models (T. Koopmans, ed.). Cowles Commission, Monograph 10, Wiley, New York, 245–257.
- Koopmans, T. (1953). Identification problems in econometric model construction. In, Studies in Econometric Method (W. Hood and T. Koopmans, eds.). Wiley, New York, 27–48.
- Marschak, J. (1950). Statistical inference in economics. In, Statistical Inference in Dynamic Economic Models (T. Koopmans, ed.). Wiley, New York, 1–50. Cowles Commission for Research in Economics, Monograph 10.
- Pearl, J. (1988)., Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Mateo, CA.
- Pearl, J. (2001). Direct and indirect effects. In, Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann, San Francisco, CA, 411–420.
- Robins, J. (1989). The analysis of randomized and non-randomized aids treatment trials using a new approach to causal inference in longitudinal studies. In, Health Service Research Methodology: A Focus on AIDS (L. Sechrest, H. Freeman and A. Mulley, eds.). NCHSR, U.S. Public Health Service, Washington, D.C., 113–159.
- Wermuth, N. (1992). On block-recursive regression equations., Brazilian Journal of Probability and Statistics (with discussion) 6 1–56.
- Cole, P. (1997). Causality in epidemiology, health policy, and law., Journal of Marketing Research 27 10279–10285.
- Pearson, K., Lee, A. and Bramley-Moore, L. (1899). Genetic (reproductive) selection: Inheritance of fertility in man., Philosophical Transactions of the Royal Society A 73 534–539.
- Robertson, D. (1997). The common sense of cause in fact., Texas Law Review 75 1765–1800.
Cited by
Items 701–800 of 2,354
Re-assessing human mortality risks attributed to PM2.5-mediated effects of agricultural ammonia
Cox, L. A. (2023) · Environmental Research · doi:10.1016/j.envres.2023.115311 · Cited by 14
Testing Causality in Scientific Modelling Software
Clark, A. G., Foster, M. S., Prifling, B., Walkinshaw, N., Hierons, R. M., Schmidt, V., & Turner, R. D. (2023) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3607184 · Cited by 32
“This problem is commonly captured by the adage: “correlation does not imply causation”.”
BackgroundZgaga, L., Agakov, F. V., Τheodoratou, E., Farrington, S. M., Tenesa, A., Dunlop, M. G., McKeigue, P., & Campbell, H. (2013) · PLoS ONE · doi:10.1371/journal.pone.0063475 · Cited by 16
Directed information and pearl's causal calculus
Raginsky, M. (2011) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2011.6120270 · Cited by 14
Causal discovery from sequential data in ALS disease based on entropy criteria
Ahangaran, M., Jahed‐Motlagh, M. R., & Bidgoli, B. M. (2018) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2018.10.004 · Cited by 14
Gıovanıs, E. (2019) · International Journal of Computational Economics and Econometrics · doi:10.1504/ijcee.2019.097795 · Cited by 25
Research Note: Causal inference
Herbert, R. (2020) · Journal of physiotherapy · doi:10.1016/j.jphys.2020.07.010 · Cited by 14
The Hitchhiker’s Guide to Computational Linguistics in Suicide Prevention
Ophir, Y., Tikochinski, R., Klomek, A. B., & Reichart, R. (2021) · Clinical Psychological Science · doi:10.1177/21677026211022013 · Cited by 23
Capuchin: Causal Database Repair for Algorithmic FairnessPreprint
Salimi, B., Rodriguez, L., Howe, B., & Suciu, D. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.08283 · Cited by 12
“Proxy Fairness To avoid individual-level counterfactuals, a common is to study population-level counterfactuals or interventional distributions that capture the effect of interventions at population level rather than individual level [37, 39, 40].”
BackgroundDiscovering Nonlinear Relations with Minimum Predictive Information RegularizationPreprint
Wu, T., Breuel, T. M., Skuhersky, M., & Kautz, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.01885 · Cited by 40
“Pearl [32, 33, 34] defines causality in terms of intervention and structural dependence, under the structural equation models (SEM).”
BackgroundStatistical Foundations of Actuarial Learning and its ApplicationsPreprint
Wüthrich, M. V., & Merz, M. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3822407 · Cited by 14
A fair price to pay: Exploiting causal graphs for fairness in insurance
Côté, O., Côté, M., & Charpentier, A. (2025) · Journal of Risk & Insurance · doi:10.1111/jori.12503 · Cited by 24
Simulation extrapolation method for measurement error: A review
Sevilimedu, V., & Yu, L. (2022) · Statistical Methods in Medical Research · doi:10.1177/09622802221102619 · Cited by 19
“Causal inference is a field of statistics that links causal knowledge (structure of causation) of an event of interest, with applied mathematics, thereby aiding in making inferences of a causal association between the event and a stipulated cause.(64) The establishment of causation also requires that certain epidemiol…”
Multivariate analysis of peptide-driven nucleation and growth of Au nanoparticles
Lachowski, K. J., Vaddi, K., Naser, N. Y., Baneyx, F., & Pozzo, L. D. (2022) · Digital Discovery · doi:10.1039/d2dd00017b · Cited by 12
A workflow for causal inference in cross-cultural psychology
Bulbulia, J. A. (2022) · Religion Brain & Behavior · doi:10.1080/2153599x.2022.2070245 · Cited by 17
“For this reason, reporting “ predictions ” in the absence of a causal framework is likely to mislead (Bulbulia et al., 2021; Her-nán, 2018; McElreath, 2020; Pearl, 2009; Rohrer, 2018; VanderWeele, 2015; Westreich & Green-land, 2013).”
BackgroundEstimating Average Causal Effects from Patient Trajectories
Frauen, D., Hatt, T., Melnychuk, V., & Feuerriegel, S. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i6.25921 · Cited by 33
Medium- and Long-Term Load Forecasting for Power Plants Based on Causal Inference and Informer
Yang, K., & Shi, F. (2023) · Applied Sciences · doi:10.3390/app13137696 · Cited by 13
Learning for Counterfactual Fairness from Observational Data
Ma, J., Guo, R., Zhang, A., & Li, J. (2023) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3580305.3599408 · Cited by 30
“It is built upon the Pearl’s causal framework [39], which is defined as a triple (U ,V , F ) such that:”
BackgroundCRAB: Assessing the Strength of Causal Relationships Between Real-world Events
Romanou, A., Montariol, S., Paul, D., Laugier, L., Aberer, K., & Bosselut, A. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.940 · Cited by 36
Evaluating the social benefits and network costs of heat pumps as an energy crisis intervention
Zhou, Y., Essayeh, C., Darby, S. J., et al. (2024) · iScience · doi:10.1016/j.isci.2024.108854 · Cited by 13
An Overview of Real-World Data Infrastructure for Cancer Research
Price, G. J., Peek, N. B., Eleftheriou, I., Spencer, K. L., Paley, L., Hogenboom, J., van Soest, J., Dekker, A. L. A. J., van Herk, M., & Finn, C. F. (2024) · Clinical Oncology · doi:10.1016/j.clon.2024.03.011 · Cited by 18
The limits of inference: reassessing causality in international assessments
Rutkowski, D., Rutkowski, L. A., Thompson, G., & Canbolat, Y. (2024) · Large-scale Assessments in Education · doi:10.1186/s40536-024-00197-9 · Cited by 14
“Additionally, the identification of a ‘cause’ must eliminate other plausible alternative explanations for the observed relationship, ensuring that the connection between cause and effect is both direct and unambiguous (Pearl, 2009; Shadish et al., 2002).”
BackgroundMethodInfluentialData-driven dimensionality reduction and causal inference for spatiotemporal climate fields
Falasca, F., Perezhogin, P. A., & Zanna, L. (2024) · Physical review. E · doi:10.1103/physreve.109.044202 · Cited by 26
“In the last decades, new ideas from computer science, mainly driven by Pearl [31, 36], have given us practical ways to design and implement causal tools mainly based on graphical models.”
BackgroundEconometric causality: The central role of thought experiments
Heckman, J. J., & Pinto, R. R. (2024) · Journal of Econometrics · doi:10.1016/j.jeconom.2024.105719 · Cited by 26
Cox, L. A., Thompson, W. J., & Mundt, K. A. (2024) · Critical Reviews in Toxicology · doi:10.1080/10408444.2024.2337435 · Cited by 15
“Doing so fails to preserve the “basic distinction” between differences and changes that is essential for valid causal analysis and interpretation of data (Pearl 2009).”
BackgroundMethodInfluentialReview of machine learning solutions for eating disorders
Ghosh, S., Burger, P. C., Simeunovic-Ostojic, M., Maas, J., & Petković, M. (2024) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2024.105526 · Cited by 17
Overcoming Data Gaps in Life Course Epidemiology by Matching Across Cohorts
Kezios, K., Zimmerman, S. C., Buto, P. T., Rudolph, K. E., Calónico, S., Hazzouri, A. Z. A., & Glymour, M. M. (2024) · Epidemiology · doi:10.1097/ede.0000000000001761 · Cited by 15
“48 For clarity, we contextualize these variables using the example of elevated early-life blood pressure and late-life dementia risk.”
Wang, F., Li, J., Peng, D., Yi, Q., Xiaoyang Zhang, A., Zheng, J., & Chen, S. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3435699 · Cited by 13
“The main difference between causal inference and correlation inference is that causal inference analyzes the response of the effect variable when the cause changes [33].”
BackgroundKPI-oriented process monitoring based on causal-weighted partial least squares
Xue, J., Zhang, T., & Ye, H. (2024) · Information Sciences · doi:10.1016/j.ins.2024.121470 · Cited by 16
A simulation study on matched case-control designs in the perspective of causal diagrams
Li, H., Yuan, Z., Su, P., Wang, T., Yu, Y., Sun, X., & Xue, F. (2016) · BMC Medical Research Methodology · doi:10.1186/s12874-016-0206-3 · Cited by 13
“Furthermore, do-calculus together with back-door criterion proposed by Pearl [20, 24, 25] were used to calculate the causal effect of exposure (X) on outcome (Y).”
MethodInfluentialDetecting potential signals of adverse drug events from prescription data
Zhan, C., Roughead, E. E., Liu, L., et al. (2020) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2020.101839 · Cited by 13
Bhattacharjee, A., Patil, V. M., Dikshit, R. P., et al. (2020) · Head & Neck · doi:10.1002/hed.26196 · Cited by 13
“The states are expressed as E(1), E(2), E(3), and E(4) depicted in a directed acyclic graph (DAG).(8) The corresponding time shift from one state to another is defined by time T(1), T(2), T(3), and T(4), respectively (Figure 1).”
BackgroundRevisiting causality using stochastics: 1. Theory
Koutsoyiannis, D., Onof, C., Christofides, A., & Kundzewicz, Z. W. (2022) · Proceedings of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rspa.2021.0835 · Cited by 12
“[30], based on the works by Pearl [31] and Pearl et al.”
MethodExploring causal hypotheses: breaking with long‐standing research traditions
Gemert, S. L. B., & van den Heuvel, E. R. (2013) · Developmental Medicine & Child Neurology · doi:10.1111/dmcn.12269 · Cited by 13
Hepatic and pancreatic resection in patients with end-stage renal disease: a propensity analysis
Barbas, A. S., Speicher, P. J., & Clary, B. M. (2014) · HPB · doi:10.1111/hpb.12281 · Cited by 13
Causal modelling applied to the risk assessment of a wastewater discharge
Paul, W. L., Rokahr, P. A., Webb, J., Rees, G. N., & Clune, T. S. (2016) · Environmental Monitoring and Assessment · doi:10.1007/s10661-015-5074-5 · Cited by 14
“There are two broad families of causal models (Spirtes 2010) — namely, causal Bayesian networks (BNs) and structural equation models (SEMs) — which are now known to be more similar than was previously thought (Pearl 1998, 2000, 2009).”
BackgroundMethodInfluentialSkowron, A., Jankowski, A. W., & Dutta, S. (2015) · Studies in big data · doi:10.1007/978-3-319-26989-4_3 · Cited by 14
“One can observe that this is a slightly modified version of the opinion of Judea Pearl [40].”
BackgroundInfluentialCausal Analysis of Emergency Department Delays
Kheirbek, R., Beygi, S., Zargoush, M., Alemi, F., Smith, A. W., Fletcher, R. D., Seton, P. N., & Hawkins, B. A. (2015) · Quality Management in Health Care · doi:10.1097/qmh.0000000000000067 · Cited by 14
Gıovanıs, E. (2018) · Empirical Economics · doi:10.1007/s00181-018-1509-5 · Cited by 12
“Directed means that E has an asymmetric edge over V , and acyclic means that the directed edges do not form circles (Spirtes et al. 2000; Pearl 2000, 2009).”
Turk, J. M. (2019) · Research in Higher Education · doi:10.1007/s11162-019-09549-9 · Cited by 21
Abeygunawardane, D., García, A. K., Sun, Z., Müller, D., Sitoe, A. A., & Meyfroidt, P. (2022) · AMBIO · doi:10.1007/s13280-021-01682-z · Cited by 19
“…between variables (i.e., nodes), and (ii) a quantitative component with conditional probability tables (CPT) that quantify the strength of the conditional The Author(s) 2022 www.kva.se/en 123 dependencies between the variables using a set of parameters (Jensen & Nielsen, 2007; Pearl, 2009).”
Graphical Models for Probabilistic and Causal Reasoning
Pearl, J. (2014) · Chapman & Hall/CRC eBooks · doi:10.1201/b16812-50 · Cited by 18
Self-citationBurch, G. S. J., & Anderson, N. R. (2012) · Cambridge University Press eBooks · doi:10.1017/cbo9780511596544.046 · Cited by 13
Mazaheri, A., Montewka, J., & Kujala, P. (2013) · TransNav the International Journal on Marine Navigation and Safety of Sea Transportation · doi:10.12716/1001.07.01.16 · Cited by 13
“The opposite statement as “correlation does not imply causation” is widely accepted between the statisticians [20]; however, “non‐correlation implies non‐causation” is still being discussed within the statisticians and other scholars [21].”
BackgroundThree Strategies for the Critical Use of Statistical Methods in Psychological Research
Campitelli, G., Macbeth, G., Ospina, R., & Marmolejo‐Ramos, F. (2016) · Educational and Psychological Measurement · doi:10.1177/0013164416668234 · Cited by 13
“The following is a nonexhaustive list: (1) flow charts (e.g., Campitelli & Gerrans, 2014); (2) causal models, including SEM (or structural equation model; Pearl, 2009); (3) probabilistic graphical models with plate notation (e.g., Jordan, 2004; Koller, Friedman, Getoor, & Taskar, 2007; Lee, 2008; see Campitelli & Macb…”
BackgroundInfluentialGuo, R., Li, J., Li, Y., Candan, K. S., Raglin, A. J., & Liu, H. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/625 · Cited by 15
Williams, D. R., Briganti, G., Linkowski, P., & Mulder, J. (2021) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/7uhx8 · Cited by 15
More, S. J., Bampidis, V., Benford, D., Bragard, C., Hernández, A. F., Bennekou, S. H., Koutsoumanis, K. P., Lambré, C., Machera, K. A., Mennes, W. C., et al. (2024) · EFSA Journal · doi:10.2903/j.efsa.2024.8866 · Cited by 16
Causal analysis of network logs with layered protocols and topology knowledge
Kobayashi, S., Otomo, K., & Fukuda, K. (2019) · 2019 15th International Conference on Network and Service Management (CNSM) · doi:10.23919/cnsm46954.2019.9012718 · Cited by 13
“Causal inference [3] is a popular approach to extracting contextual information in automated analysis.”
MethodHason Rudd, D., Huo, H., & Xu, G. (2022) · Human-Centric Intelligent Systems · doi:10.1007/s44230-022-00006-y · Cited by 12
“Recent causal inference developments highlight fundamental alterations required to move from standard statistical analysis toward multivariate causal analysis [3].”
BackgroundPappas, J. L. (2015) · Marine Micropaleontology · doi:10.1016/j.marmicro.2015.12.001 · Cited by 12
“Causal analysis is used to model changing events and the actual and potential conditions under which such events might occur (Pearl, 2009).”
BackgroundMethodInfluentialVACA: Designing Variational Graph Autoencoders for Causal Queries
Sánchez-Martín, P., Rateike, M., & Valera, I. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i7.20789 · Cited by 63
“We highlight that certain counter-factual queries are not identifiable from observational data without making assumptions on the functional relationships even under causal sufficiency (Pearl 2009a).”
BackgroundMethodInfluentialA Brief Tour of Deep Learning from a Statistical Perspective
Nalisnick, E., Smyth, P., & Tran, D. (2023) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-032921-013738 · Cited by 19
Causality and wildlife management
Hone, J., & Krebs, C. J. (2023) · Journal of Wildlife Management · doi:10.1002/jwmg.22412 · Cited by 15
“…various analyses, including structural equation modeling (Smith et al. 1997, Grace et al. 2015), path analysis (Shipley 2009), the methods of Pearl (2009 a , b ; Arif and MacNeil 2022 should evaluate the assumptions of each alternative analysis to help identify reasons why some analyses generate…”
BackgroundMethodInfluentialNaser, M. Z., & Çiftçioğlu, A. Ö. (2023) · Fire Technology · doi:10.1007/s10694-023-01405-8 · Cited by 12
“The underlying structure is then built by satisfying three causal principles, namely the Markov causal assumption, the causal faithfulness assumption, and the causal sufficiency assumption [29–31].”
Causality extraction: A comprehensive survey and new perspective
Ali, W., Zuo, W., Wang, Y., Ali, R., Rahman, G., & Ullah, I. (2023) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2023.101593 · Cited by 19
Summarized Causal Explanations For Aggregate Views
Youngmann, B., Cafarella, M., Gilad, A., & Roy, S. (2024) · Proceedings of the ACM on Management of Data · doi:10.1145/3639328 · Cited by 14
“In Pearl’s model, a treatment 𝑇 = 𝑡 (on one or more variables) is considered as an intervention to a causal DAG by mechanically changing the DAG such that the values of node(s) for 𝑇 in 𝐺 are set to the value(s) in 𝑡 , which is denoted by do ( 𝑇 = 𝑡 ) .”
BackgroundMethodInfluentialXu, D., Hu, X., Yu, F., Deng, P., & Jia, Y. (2024) · Journal of the American Chemical Society · doi:10.1021/jacs.4c07700 · Cited by 13
You, L., Guo, N., Long, Z., Wang, F., Si, C., & Diab, A. (2024) · International Journal of Pavement Engineering · doi:10.1080/10298436.2024.2381060 · Cited by 13
“In this paper, the long-term treatment benefits of maintenance practices for longitudinal cracking in asphalt pavements are investigated, incorporating the currently dominant causal inference frameworks: the structural causal model (Pearl 2009) and the potential outcome model (Rubin 1974).”
CausalMob: Causal Human Mobility Prediction with LLMs-derived Human Intentions toward Public Events
Yang, X., Ge, H., Wang, J., Fan, Z., Jiang, R., Shibasaki, R., & Koshizuka, N. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709231 · Cited by 22
“Causal analysis aims to reveal cause-effect relationships among variables [23].”
Does positive affect mediate the association of multimorbidity on depressive symptoms?
Demirer, I., Kühhirt, M., Karbach, U., & Pfaff, H. (2021) · Aging & Mental Health · doi:10.1080/13607863.2020.1870209 · Cited by 13
“These confounding factors affect at least two variables of interest simultaneously (Pearl, 2009).”
BackgroundReflection on modern methods: combining weights for confounding and missing data
Ross, R. K., Breskin, A., Breger, T. L., & Westreich, D. J. (2021) · International Journal of Epidemiology · doi:10.1093/ije/dyab205 · Cited by 15
Fishing, predation, and temperature drive herring decline in a large marine ecosystem
Boyce, D. G., Petrie, B. D., & Frank, K. T. (2021) · Ecology and Evolution · doi:10.1002/ece3.8411 · Cited by 10
Explanatory Paradigms in Neural Networks: Towards relevant and contextual explanations
AlRegib, G., & Prabhushankar, M. (2022) · IEEE Signal Processing Magazine · doi:10.1109/msp.2022.3163871 · Cited by 23
“Note that the observed correlation features presented here are different from interventionist causal factors discussed in [25][19][10] even though the question it answers is causal.”
BackgroundEvaluation Options for Wildlife Management and Strengthening of Causal Inference
Hone, J., Drake, V. A., & Krebs, C. J. (2023) · BioScience · doi:10.1093/biosci/biac105 · Cited by 12
Hsu, D. K., Mitchell, J., & Cao, X. (2023) · Entrepreneurship Theory and Practice · doi:10.1177/10422587231152824 · Cited by 25
“There are three requirements for a variable to qualify and serve as an instrumental variable ( Z ): randomization, relevance, and exclusion (Baiocchi et al., 2014; Becker, 2016; Pearl, 2009; Sajons, 2020).”
Pakzad, R., Nedjat, S., Salehiniya, H., Mansournia, N., Etminan, M., Nazemipour, M., Pakzad, I., & Mansournia, M. A. (2023) · BMC Medical Research Methodology · doi:10.1186/s12874-023-01978-6 · Cited by 14
“The Pearl’s back-door criterion was applied to identify a minimally sufficient set for confounding adjustment [47].”
MethodConfounder balancing in adversarial domain adaptation for pre-trained large models fine-tuning
Jiang, S., Chen, Q., Xiang, Y., Pan, Y., Wu, X., & Lin, Y. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106173 · Cited by 14
Evaluating the influence of marine protected areas on surf zone fish
Marraffini, M. L., Hamilton, S. L., Jarrín, J. R. M., Ladd, M. C., Koval, G., Madden, J. R., Mangino, I., Parker, L., Emery, K., Terhaar, K. T. K., et al. (2024) · Conservation Biology · doi:10.1111/cobi.14296 · Cited by 14
“We used a structural causal modeling framework (Pearl, 2009) that employs directed acyclic graphs to visually represent causal structure of the study system (Arif & MacNeil, 2023; Laubach et al., 2021) (Figure 6a).”
Inferring network structure from interventional time-course experiments
Spencer, S. E. F., Hill, S. M., & Mukherjee, S. (2015) · The Annals of Applied Statistics · doi:10.1214/15-aoas806 · Cited by 12
“On the other hand, in contrast to static DAGs as in (2009), for feed-forward DBNs of the type considered here, the underlying DAG is identifiable (i.e., the equivalence class always contains exactly one graph).”
BackgroundMethodMasri, W. (2015) · Advances in computers · doi:10.1016/bs.adcom.2015.05.001 · Cited by 15
“Next, we provide background needed to understand the fault localization techniques that we present later and are based on causal inference, specifically Pearl’s back-door criterion [18,19].”
MethodA note on fourth moment-based direction dependence measures when regression errors are non normal
Wiedermann, W. (2017) · Communication in Statistics- Theory and Methods · doi:10.1080/03610926.2017.1388403 · Cited by 12
“It is well known that the causal effect, say, βyx is identifiable and can validly be quantified via the OLS estimate byx = cov(x, y)/σ 2 x only if x and εyx are uncorrelated (cf., Clogg and Haritou 1997; Pearl 2009).”
BackgroundDevelopment of a protocol for environmental impact studies using causal modelling
Hatami, R. (2018) · Water Research · doi:10.1016/j.watres.2018.03.034 · Cited by 14
Dealing with observational data in control
Wilson, E. D., Clairon, Q., Henderson, R., & Taylor, C. J. (2018) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2018.05.001 · Cited by 12
“Consequently, as Pearl (2009) states, behind every causal conclusion there must lie some causal assumption that is not testable in observational studies.”
BackgroundChawala, S., Pund, A., Vibishan, B., Kulkarni, S., Diwekar-Joshi, M., & Watve, M. (2018) · PLoS ONE · doi:10.1371/journal.pone.0204755 · Cited by 14
“The Rubin Causal Model also incorporates the structural 52 equations model as it includes non-parametric forms as well (16,17).”
MethodLi, X., & Wiedermann, W. (2019) · Multivariate Behavioral Research · doi:10.1080/00273171.2019.1687276 · Cited by 15
“A causal model of the form x! y implies that changing x (the cause) changes y (the effect) but changing y will not cause any changes in x (Pearl, 2009; Peters, Janzing, & Sch€olkopf, 2017).”
BackgroundHan, S., & Kim, H. M. (2020) · TED EĞİTİM VE BİLİM · doi:10.15390/eb.2020.7386 · Cited by 25
FairyTED: A Fair Rating Predictor for TED Talk Data
Acharyya, R., Das, S., Chattoraj, A., & Tanveer, M. I. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i01.5368 · Cited by 7
Robinson, M. D., & Sedikides, C. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.031 · Cited by 19
Thorson, J. T., Hermann, A. J., Siwicke, K. A., et al. (2020) · ICES Journal of Marine Science · doi:10.1093/icesjms/fsaa236 · Cited by 12
“density (Pearl, 2009), and process research is necessary to measure dependencies among variables (P) in order to accurately predict”
BackgroundTowards a unified framework to study causality in Earth–life systems
Dolby, G. (2021) · Molecular Ecology · doi:10.1111/mec.16142 · Cited by 11
“Judea Pearl largely formalized the algorithmic and mathematical definition of causality (Hopkins & Pearl, 2007; Pearl, 1995, 1998, 2009; Pearl & Verma, 1995), which is key for modelling systems in a way where new knowledge can be learned beyond what is already observed.”
BackgroundExamining the Causal Effects of Road Networks on Landscape Ecological Risk: The Case of Wuhan, China
Tan, R., & Zhou, K. (2023) · Journal of Urban Planning and Development · doi:10.1061/jupddm.upeng-3963 · Cited by 15
Classical and causal inference approaches to statistical mediation analysis
García, M. A., Vallejo, G., & Lozano, E. A. (2014) · Psicothema · doi:10.7334/psicothema2013.314 · Cited by 13
“Identifying indirect (ACME ) and direct (ADE) causal effects requires what is known as the Sequential Ignorability (SI) assumption (see Robins & Greenland, 1992; Pearl, 2009) which consists of two parts: (A) given one or more observed covariates, the treatment is ignorable, that is, independent of the potential values…”
InfluentialGrant, E. J., COLOGNE, J. B., Sharp, G. B., Eguchi, H., Stevens, R. G., Izumi, S., Kim, Y.-M., de González, A. B., Ohishi, W., & Nakachi, K. (2018) · International Journal of Radiation Biology · doi:10.1080/09553002.2018.1419303 · Cited by 13
“Causal modeling methods to assess mediation (Pearl 2009; Lange and Hansen 2011) cannot be immediately applied to counter-matched, nested case-control data.”
MethodThe Impact of Coffee Certification on Small-Scale Producers’ Livelihoods: Evidence from EthiopiaPreprint
Jena, P. R., Stellmacher, T., & Grote, U. (2012) · RePEc: Research Papers in Economics · doi:10.22004/ag.econ.126720 · Cited by 12
Interpretable Conditions for Identifying Direct and Indirect Effects
Pearl, J. (2012) · Defense Technical Information Center (DTIC) · doi:10.21236/ada564093 · Cited by 14
Self-citationDesigning digital health interventions with causal inference and multi-armed bandits: a review
Švihrová, R., Rossi, A. D., Marzorati, D., Tzovara, A., & Faraci, F. D. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1435917 · Cited by 18
Multimodal Wearable Biosensing Meets Multidomain AI: A Pathway to Decentralized Healthcare
Liu, C., Fan, H., Kim, M., Zhou, T., Yang, P., Zhao, L., Wang, Y., Che, Z., Liu, C., Li, B., et al. (2026) · Advanced Science · doi:10.1002/advs.202522900 · Cited by 31
“…can be supported by interpretability and causal analysis tools, including feature attribution [ 198 ], attention maps [ 199 ], causal graphs [ 200, 201 ], and counterfactual explanations [ 197 ], which probe decision sensitivity and help distinguish clinically meaningful dependencies from…”
Rentala, G. S., Zhu, Y., & Mukhopadhyay, S. (2021) · Frontiers in Sustainable Cities · doi:10.3389/frsc.2021.730474 · Cited by 11
Deutch, D., Gilad, A., Milo, T., Mualem, A., & Somech, A. (2022) · Proceedings of the VLDB Endowment · doi:10.14778/3565838.3565841 · Cited by 11
“Our definition of contribution draws on the notion of intervention, first defined in the context of causality [54] to measure the change in the outcome”
BackgroundA coordinated ramp metering framework based on heterogeneous causal inference
Peng, C., & Xu, C. (2023) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12994 · Cited by 12
“Min, Minimize. the outcome variable resulting from a unit increase in the treatment variable (Holland, 1986; Pearl, 2009).”
BackgroundEdwards, D. J. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1150743 · Cited by 13
“…(Pearl, 2000) has been successfully applied to causal reasoning (action and change) in artificial intelligence (AI; Pearl, 1988), statistics, economics (Pearl, 2009), social sciences (Pearl, 2000), and even as Bayesian networks represented as propositional reasoning in cognition (Pearl, 2011).”
MethodA novel adaptive multi-scale Rényi transfer entropy based on kernel density estimation
Zhang, J., Cao, J., Wu, T., Huang, W. D., Ma, T., & Zhou, X. (2023) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2023.113972 · Cited by 11
Fetene, S. M., Yitayal, M., & Aschalew, A. Y. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2023.1078462 · Cited by 14
“This included covariates that occurred before the program and covariates that are highly associated with the outcome (63) as well as covariates that affect the membership of the program and the outcomes (64).”
BackgroundSocial Protection in Latin America: Causality, Stratification and Outcomes
Barrientos, A. (2024) · Global dynamics of social policy · doi:10.1007/978-3-031-49795-7 · Cited by 52
Hönigsberger, F., Saranti, A., Jalali, A., Stampfer, K., & Holzinger, A. (2024) · Applied Sciences · doi:10.3390/app14093911 · Cited by 12
The migration of hydrogen in sedimentary basins
Lodhia, B. H., & Peeters, L. J. M. (2024) · Australian Energy Producers journal. · doi:10.1071/ep23176 · Cited by 13
OTClean: Data Cleaning for Conditional Independence Violations using Optimal Transport
Pirhadi, A., Moslemi, M. H., Cloninger, A., Milani, M., & Salimi, B. (2024) · Proceedings of the ACM on Management of Data · doi:10.1145/3654963 · Cited by 20
“It underpins causal reasoning and graphical models, serving as a cornerstone for efficient probabilistic inference [31, 38].”
Causal features in turbulent channel flow
Osawa, K., & Jiménez, J. (2024) · Journal of Fluid Mechanics · doi:10.1017/jfm.2024.838 · Cited by 11
Response Theory via Generative Score Modeling
Giorgini, L. T., Deck, K., Bischoff, T., & Souza, A. (2024) · Physical Review Letters · doi:10.1103/physrevlett.133.267302 · Cited by 13
Metadata
- Authors
- Pearl, J.
- Affiliations
- University of California, Los Angeles (US)
- Corresponding author
- Pearl, Judea
- Venue
- Statistics Surveys
- Publisher
- Institute of Mathematical Statistics
- Published
- 2009-01-01
- Volume
- 3
- Issue
- none
- Pages
- 96-146
- ISSN
- 1935-7516 (ISSN-L)
- OpenAlex
- W2143117649
- Cited by
- 2,336
- References
- 135
- Citations by year
- 2026: 184 · 2025: 273 · 2024: 271 · 2023: 245 · 2022: 215 · 2021: 208 · 2020: 243 · 2019: 140 · 2018: 96 · 2017: 77 · 2016: 82 · 2015: 82 · 2014: 63 · 2013: 65 · 2012: 46
- FWCI
- 25.47
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Statistics Surveys (publishedVersion, cc-by)
- Project Euclid (Cornell University) (submittedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- Department of Statistics, UCLA
- Funders
- Office of Naval Research
- 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 inference, structural causal models, counterfactual reasoning, causal assumptions, causal effects, policy evaluation, intervention effects, regret, causal attribution, direct and indirect effects, mediation analysis
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.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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.