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 1,101–1,200 of 2,354
Ding, T., Hasan, F., Bickel, W. K., & Pan, S. (2020) · International Journal of Artificial Intelligence Tools · doi:10.1142/s021821302060009x · Cited by 6
Sample selection bias in evaluation of prediction performance of causal models
Long, J. P., & Ha, M. J. (2021) · Statistical Analysis and Data Mining The ASA Data Science Journal · doi:10.1002/sam.11559 · Cited by 6
“Causal estimands may be formally expressed in the Neyman–Rubin potential– outcomes framework or via Pearl counterfactuals derived from structural Equations [10, 7].”
MethodEmmert‐Streib, F., Manjang, K., Dehmer, M., et al. (2021) · Cancers · doi:10.3390/cancers13205087 · Cited by 6
“Unfortunately, this does not correspond to a causal analysis [37,38] in the strict sense but merely to associations.”
BackgroundExplaining Machine Learning by Bootstrapping Partial Dependence Functions and Shapley Values
Cook, T. R., Gupton, G. M., Modig, Z., & Palmer, N. (2021) · The Federal Reserve Bank of Kansas City Research Working Papers · doi:10.18651/rwp2021-12 · Cited by 12
Methods and Applications of Causal Reasoning in Medical Field
Wu, X., Li, J., Qian, Q., Liu, Y., & Guo, Y. (2021) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia53151.2021.9619639 · Cited by 8
Deep treatment-adaptive network for causal inference
Li, Q., Wang, Z., Liu, S., Li, G., & Xu, G. (2022) · The VLDB Journal · doi:10.1007/s00778-021-00724-y · Cited by 8
“The standard way to account for treatment effect is by “controlling” the confounders from the observed covariates [31, 32].”
BackgroundInfluentialReinforcement Learning of Causal Variables Using Mediation Analysis
Herlau, T., & Larsen, R. F. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i6.20648 · Cited by 15
“Statistical causal analysis, as developed and popularized by Judea Pearl, assumes that data arises as transformations of noise sources according to a causal graph (Pearl 2009).”
Serrano-Mira, L., Maroto, M. P., Ayra, E. S., et al. (2022) · Aerospace · doi:10.3390/aerospace9090513 · Cited by 6
“An edge in a BN shows a probabilistic dependency between two nodes; however, it does not imply a causality relationship between them because causality is a relationship, which cannot be defined only from the joint distribution [28].”
BackgroundAdvanced Analysis of Dynamic Graphs in Social and Neural Networks
Held, P., Moewes, C., Braune, C., Kruse, R., & Sabel, B. A. (2012) · Studies in fuzziness and soft computing · doi:10.1007/978-3-642-30278-7_17 · Cited by 8
“There might not be any causal coherence [23].”
BackgroundCausal Modelling in Enterprise Architecture Frameworks
Gudas, S. (2021) · Informatica · doi:10.15388/21-infor446 · Cited by 9
mRSC: Multi-dimensional Robust Synthetic Control
Amjad, M. J., Misra, V., Shah, D., & Shen, D. (2019) · Proceedings of the ACM on Measurement and Analysis of Computing Systems · doi:10.1145/3341617.3326152 · Cited by 35
“Causal inference has long been an interest for researchers from a wide array of communities, ranging from economics to machine learning (see [18, 19, 21, 22] and the references therein).”
BackgroundKuesten, C. L., Dang, J., Nakagawa, M., Bi, J., & Meiselman, H. L. (2016) · Food Quality and Preference · doi:10.1016/j.foodqual.2016.02.020 · Cited by 7
Bruskotter, J. T., Vucetich, J. A., Smith, D. W., et al. (2017) · Food Webs · doi:10.1016/j.fooweb.2017.05.004 · Cited by 6
Joint Structure Learning of Multiple Non-Exchangeable NetworksPreprint
Oates, C. J., & Mukherjee, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1402.5640 · Cited by 6
“Thus in our formulation, inferred causation is explicitly conditional on prior causal hypotheses G0 (Pearl, 2009).”
BackgroundMethodInfluentialThe mathematics of causal inference
Pearl, J. (2011) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2020408.2020416 · Cited by 10
Self-citationMelamed, I. D., & Gilbert, M. (2011) · Wiley eBooks · doi:10.1002/9781119992691.ch14 · Cited by 8
Galas, D. J., Sakhanenko, N. A., Skupin, A., et al. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1302.6932 · Cited by 6
“The introduction of directionality in the hypergraphs could be used to extend the present theory into the realm of representation of causality models as discussed by Pearl (2009, 2010).”
Learning Individual Causal Effects from Networked Observational DataPreprint
Guo, R., Li, J., & Liu, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.03485 · Cited by 6
“e fact that the causal relationships between variables are unknown, the strong ignoralbility assumption becomes untenable and it is likely to be unrealistic due to the existence of hidden confounders [18]. Recently, a series of methods are proposed to leverage representation learning to relax the strong ignorability a…”
BackgroundCausal Relational LearningPreprint
Salimi, B., Parikh, H., Kayali, M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.03644 · Cited by 6
“l models give semantics to interventions. An intervention represents actively setting an endogenous variable to some fixed value and observing the effect denoted by the do-operator introduced by Pearl [38]. Formally, an intervention do(W = w) consists of setting variables W V to some values W = w, and it defines the pro…”
Counterfactual Variable Control for Robust and Interpretable Question AnsweringPreprint
Yu, S., Niu, Y., Wang, S., Jiang, J., & Sun, Q. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.05581 · Cited by 8
“CVC in essence includes counterfactual analysis (Pearl et al. 2009; Pearl and Mackenzie 2018; Pearl 2001) and variable control .”
BackgroundMethodInfluentialFSPN: A New Class of Probabilistic Graphical ModelPreprint
Wu, Z., Zhu, R., Pfadler, A., Han, Y., Li, J., Qian, Z., Zeng, K., & Zhou, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.09020 · Cited by 15
“They are more appliable in lots of tasks such as online causal inference (Pearl et al., 2009) and query selectivity estimation (Getoor & Taskar, 2001), which have strict requirements on both inference accuracy and speed of the deployed models.”
BackgroundContrastive Reasoning in Neural NetworksPreprint
Prabhushankar, M., & AlRegib, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12329 · Cited by 13
“The factors that cause P are termed causal reasons [15], [41].”
BackgroundHuman Trajectory Prediction via Counterfactual AnalysisPreprint
Chen, G., Li, J., Lu, J., & Zhou, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.14202 · Cited by 5
“Causal Inference: Different from conventional associated inference, the causal inference aims to investigate the effect of variables when some cause is changed [34, 33].”
BackgroundQuantifying Causal Pathways of Teleconnections
Kretschmer, M. (2022) · EGU General Assembly Conference Abstracts · doi:10.5194/egusphere-egu22-8246 · Cited by 9
Ethics and the explainable artificial intelligence(XAI) movementPreprint
Adamson, G. (2022) · doi:10.36227/techrxiv.20439192.v1 · Cited by 9
A Practical Guide to Causal Inference in Three-Wave Panel StudiesPreprint
Bulbulia, J. A. (2024) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/uyg3d · Cited by 5
Hasani, W. S. R., Musa, K. I., Chen, X. W., & Cheng, K. Y. (2024) · Scientific Reports · doi:10.1038/s41598-024-80091-0 · Cited by 9
Toward rough set based insightful reasoning in intelligent systems
Skowron, A., & Stepaniuk, J. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122078 · Cited by 6
Causal Time-aware News Recommendations with Large Language Models
Huang, S., Li, Q., Yang, H., Yu, D., Li, Q., & Xu, G. (2025) · ACM Transactions on Information Systems · doi:10.1145/3729422 · Cited by 8
“Inspired by previous works on causality [2, 21], we employ a commonly used stratification method to retrieve the independence between the treatment news V and time-variant covariates C in Figure 2, allowing for separate modeling of the covariates and the treatment.”
Trophic disruption by an invasive species linked to altered energy fluxes
Flood, P. J., Strickland, B. A., Loftus, W. F., & Trexler, J. C. (2025) · Ecosphere · doi:10.1002/ecs2.70266 · Cited by 7
Chen, J., Zhu, H., Xiao, B., & Ma, T. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111812 · Cited by 7
A data-driven approach for spatio-temporal causal analysis in large-scale urban traffic networks
Dong, P., Zhang, X., & Zhang, X. (2025) · Transportation Research Part E Logistics and Transportation Review · doi:10.1016/j.tre.2025.104244 · Cited by 8
How life-cycle real-world evidence can bridge evidentiary gaps in precision oncology
Krebs, E., Weymann, D., Bubela, T. M., & Regier, D. A. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1563950 · Cited by 6
Introduction to Quantitative Research
Almusaed, A., Almssad, A., & Yitmen, İ. (2025) · Springer eBooks · doi:10.1007/978-3-031-97393-2_15 · Cited by 16
Cheng, F., Zouhar, V., Chan, R. S. M., Fürst, D., Strobelt, H., & El‐Assady, M. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3634646 · Cited by 33
“Counterfactuals are an essential concept in causal reasoning and analysis, which means hypothetical “what-if” conditions [17,26,30,42].”
Averochkin, G. M., Zlobin, I., Bespalov, I., & Alexandrov, E. (2026) · Chemical Engineering Science · doi:10.1016/j.ces.2026.123732 · Cited by 6
A Bayesian Hierarchical Model for Extracting Individuals’ Theory-Based Causal Knowledge
Hans, A., Chaudhari, A. M., Bilionis, I., & Panchal, J. H. (2022) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4055596 · Cited by 5
The future of psychophysiology, then and now
Marder, M. A., & Miller, G. A. (2024) · Biological Psychology · doi:10.1016/j.biopsycho.2024.108792 · Cited by 8
“SEM and network analyses, seeing great growth in interest including for causal reasoning (e.g., Pearl, 2009), can be understood as a further extension; ditto cybernetic frameworks (Braiten-berg, 1984; DeYoung & Krueger, 2023; Diehl et al., 2023; Jin, Jonas, & Mohanty, 2023; Powers, 1973).”
BackgroundUnbiased Semantic Representation Learning Based on Causal Disentanglement for Domain Generalization
Jin, X., Li, N., Kong, W., Tang, J., & Yang, B. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3659953 · Cited by 5
“In the SCM, we observe how C confounds X and Y through the backdoor path X ← C → Y [41].”
Long-term causal effects estimation via latent surrogates representation learning
Cai, R., Chen, W., Yang, Z., Wan, S., Zheng, C., Yang, X., & Guo, J. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106336 · Cited by 11
(Vision Paper) A Vision for Spatio-Causal Situation Awareness, Forecasting, and Planning
Azad, F. T., Candan, K. S., Kapkiç, A., Li, M., Liu, H., Mandal, P., Sheth, P., Arslan, B., Chowell, G., Sabo, J. L., et al. (2024) · ACM Transactions on Spatial Algorithms and Systems · doi:10.1145/3672556 · Cited by 8
“Causal graphs, where each edge denotes a causal relationship between a pair of variables, have been popularized by Pearl [132].”
BackgroundInfluentialmetAScritic: Reframing AS-Level Topology Discovery as a Recommendation System
Salamatian, L., Vermeulen, K., Cunha, Í. F. S., Giotsas, V., & Katz-Bassett, E. (2024) · ACM Internet Measurement Conference (IMC) · doi:10.1145/3646547.3688429 · Cited by 7
“In causal inference, this property is known as conditional ignorability, or unconfoundedness [121].”
Integrating predictive modeling and causal inference for advancing medical science
Oh, T. (2024) · Childhood Kidney Diseases · doi:10.3339/ckd.24.018 · Cited by 4
Are All Policymakers Data Scientists Now? Data, Data Science and Evidence in Policymaking
Guerrero, O. A., & Margetts, H. Z. (2024) · LSE Public Policy Review · doi:10.31389/lseppr.116 · Cited by 11
Impact of Physical Activity on Quality of Life During Pregnancy: A Causal ML Approach
Kazemi, K., Ryhtä, I., Azimi, I., Niela‐Vilén, H., Axelin, A., Rahmani, A. M., & Liljeberg, P. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10782584 · Cited by 9
A Review of Causal Methods for High-Dimensional Data
Berkessa, Z. A., Läärä, E., & Waldmann, P. (2024) · IEEE Access · doi:10.1109/access.2024.3524261 · Cited by 9
Whole-brain causal discovery using fMRI
Arab, F., Ghassami, A., Jamalabadi, H., Peters, M. A. K., & Nozari, E. (2025) · Network Neuroscience · doi:10.1162/netn_a_00438 · Cited by 13
“A wide range of algorithmic solutions have been proposed [7, 18, 36, 38–45], which are often classified based on their methodology into constraint-based [33, 34, 46], noise-based [43,47], and score-based [48,49].”
Grasping Causality for the Explanation of Criticality for Automated Driving
Koopmann, T., Putze, L., Westhofen, L., Gansch, R., Adee, A., & Neurohr, C. (2025) · IEEE Access · doi:10.1109/access.2025.3555177 · Cited by 12
“In the work at hand, we combine the framework of causal theory [3] with the criticality analysis as a novel approach to tackle the problem of modeling and analyzing the causal relations of such criticality phenomena for ADSs with formal rigor.”
InfluentialFairCoRe: Fairness-aware Recommendation through Counterfactual Representation Learning
Bin, C., Liu, W., Zhang, F., Chang, L., & Gu, T. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3557501 · Cited by 12
“Our work is related to Counterfactual Thinking [29], a psychological concept that enables individuals to make hypothetical assumptions about past events to infer potential biases in the outcomes.”
Xu, H., Xu, Y., Li, C., & Zhuang, F. (2025) · ACM Transactions on Information Systems · doi:10.1145/3731447 · Cited by 7
“For CSA-VAE, we tune the hyper-parameter concepts 𝑘 in the range of [ 1 , 2 , 4 , 8 , 16 , 32 ] for different datasets.”
InfluentialCausality in Process Systems Engineering: Fundamentals, Applications, and Emerging Trends
Paredes, R., & Reis, M. S. (2025) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2025.109345 · Cited by 8
Chemical Stressors and Ecological Risk
Sparling, D. W. (2016) · Elsevier eBooks · doi:10.1016/b978-0-12-801947-4.00013-5 · Cited by 5
Cobbs, J., Jensen, J. A., & Tyler, B. D. (2021) · Journal of Business and Industrial Marketing · doi:10.1108/jbim-06-2020-0299 · Cited by 5
A Defence of Manipulationist Noncausal Explanation: The Case for Intervention Liberalism
Emmerson, N. (2021) · Erkenntnis · doi:10.1007/s10670-021-00497-4 · Cited by 8
“Also see: Hitchock (2001), Pearl (2009) and Briggs (2012).”
BackgroundLearning Discriminative Representation Base on Attention for Uplift
Xu, G., Yin, C., Zhang, Y., Li, Y., He, Y., Cai, J., & Wei, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-05981-0_16 · Cited by 5
Lee, G. K., & Bettis, R. (2022) · Strategy Science · doi:10.1287/stsc.2022.0169 · Cited by 7
Fish, B., & Stark, L. (2022) · Conference on Equity and Access in Algorithms, Mechanisms, and Optimization · doi:10.1145/3551624.3555296 · Cited by 9
“For an introduction to causal models and graphs, see Pearl [63].”
BackgroundTai, A., & Lin, S. (2022) · Statistical Methods in Medical Research · doi:10.1177/09622802221130580 · Cited by 5
Somers, R. J., Clark, A. G., Walkinshaw, N., et al. (2022) · doi:10.1145/3550356.3561589 · Cited by 5
“Testing more complex behaviour could require the use of causal mediation analysis [13], allowing for paths of multiple causal relationships to be observed.”
BackgroundLittle, D. (2023) · Texts in quantitative political analysis · doi:10.1007/978-3-031-12982-7_2 · Cited by 9
Unlock the Potential of Counterfactually-Augmented Data in Out-Of-Distribution Generalization
Fan, C., Chen, W., Tian, J., Li, Y., He, H., & Jin, Y. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122066 · Cited by 8
“From the perspective of causal learning (Yao et al., 2021), causality is a more fine-grained description of dataset beyond statistics (Pearl, 2009), and machine learning models, on the other hand, are statistical models based on probability distributions (Shah et al., 2020), so they lack the…”
BackgroundDesign and Validation of Structural Causal Model: A Focus on EGRA Dataset
Ayem, G. T., Asilkan, Ö., & Iorliam, A. (2023) · Journal of Computing Theories and Applications · doi:10.33633/jcta.v1i2.9304 · Cited by 6
“One of the most pervasive objective validation tests for SCM is the use of conditional independence testing (CIT) criteria [7, 45, 57-60].”
MethodMeasuring Bias in a Ranked List Using Term-Based Representations
Abolghasemi, A., Azzopardi, L. A., Askari, A., de Rijke, M., & Verberne, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56069-9_1 · Cited by 15
“Our evaluation is related to coun-terfactual fairness measurements which require that the same outcome should be achieved in the real world as in the term-based counterfactual world [35,51].”
BackgroundDiagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach
Chen, Z., Zheng, Y., Lai, Z., Guan, Q., & Lin, L. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i10.29028 · Cited by 7
Nassir, M., & Benoliel, P. S. (2024) · Journal of School Violence · doi:10.1080/15388220.2024.2387154 · Cited by 7
“Finally, one possible additional model (Model 3) was the reverse causality model, which reverses the direction of selected structural paths to estimate the level to which one construct occurs to “cause” another (V1 → V2) or vice versa (V2 → V1) (Pearl, 2009).”
Markov Blanket Composition of SLOs
Sedlak, B., Pujol, V. C., Donta, P. K., & Dustdar, S. (2024) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge62653.2024.00025 · Cited by 6
“Bayesian Networks (BNs), as applied by Pearl [21], are structural causal models that can be represented as a Directed Acyclic Graph (DAG): edges between variables (e.g., quality Ñ latency ) indicate conditional dependencies.”
BackgroundDiffusing High-level SLO in Microservice Pipelines
Sedlak, B., Pujol, V. C., Donta, P. K., & Dustdar, S. (2024) · IEEE International Symposium on Service-Oriented System Engineering (SOSE) · doi:10.1109/sose62363.2024.00008 · Cited by 7
“Bayesian Networks (BNs), as applied by Pearl [10], are structural causal models that can be represented as Directed Acyclic Graph (DAG); see Figure 1 for an example graph that is trained in Section IV-C.”
BackgroundAn education model to empower women in tech entrepreneurship
de Paiva, T. M. D., Felgueira, T., Alves, C. A., Gomes, N. F., Salgado, S., & Salaberri, M. (2024) · Frontiers in Education · doi:10.3389/feduc.2024.1474584 · Cited by 17
Understanding digital therapeutics in disease self-management: A systematic literature review
Yang, L., Zhang, M., Jia, L., Yan, Z., & Yin, Q. (2025) · Technology in Society · doi:10.1016/j.techsoc.2025.102831 · Cited by 9
Courbron, C. (2012) · Digital Commons (Liberty University) · Cited by 8
Inference of Causal Relationships between Biomarkers and Outcomes in High Dimensions
Agakov, F. V., McKeigue, P., Krohn, J. P., & Flint, J. (2011) · DOAJ (DOAJ: Directory of Open Access Journals) · Cited by 5
Interactive Computations: Toward Risk Management in Interactive Intelligent Systems
Jankowski, A. W., Skowron, A., & Świniarski, R. W. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-45062-4_1 · Cited by 5
A Novel Approach for Identifying Causal Models of Complex Diseases from Family Data
Park, L., & Kim, J. H. (2015) · Genetics · doi:10.1534/genetics.114.174102 · Cited by 6
“Regarding causation in epidemiology, there are other types of concepts of causation such as probabilistic causation and counterfactuals (Parascandola and Weed 2001), which include elaborate efforts to apply genetic epidemiology to studying causation based on directed acyclic graphs (Pearl 2009a,b).”
BackgroundMethodCausal dynamic effects in regional systems of technological activities: a SVAR approach
Brenner, T., & Duschl, M. (2015) · The Annals of Regional Science · doi:10.1007/s00168-015-0678-9 · Cited by 5
A Causal Model Using Self-Organizing Maps
Chung, Y., & Takatsuka, M. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-26535-3_67 · Cited by 4
Siregar, P., Julen, N., Hufnagl, P., & Mutter, G. L. (2018) · Biosystems · doi:10.1016/j.biosystems.2018.07.002 · Cited by 6
Innovation Representation of Stochastic Processes With Application to Causal Inference
Painsky, A., Rosset, S., & Feder, M. (2019) · IEEE Transactions on Information Theory · doi:10.1109/tit.2019.2927530 · Cited by 5
“We say that Y causes X (Y → X , a notation borrowed from [13], [20]) if PX |do(y=y) = PX |do(Y=y ) for some y = y .”
BackgroundGreenwood, C. J., Youssef, G. J., Letcher, P., Spry, E., Thomson, K., Hagg, L. J., Hutchinson, D. M., Macdonald, J. A., McIntosh, J. E., Sanson, A. V., et al. (2020) · Addictive Behaviors · doi:10.1016/j.addbeh.2020.106597 · Cited by 5
Bayesian Causal Inference in Probit Graphical Models
Castelletti, F., & Consonni, G. (2021) · Bayesian Analysis · doi:10.1214/21-ba1260 · Cited by 9
“A causal question involves the data generating mechanism after an intervention is applied to the system, and must be carefully distinguished from traditional conditioning of probability theory (Pearl, 2009, Section 2.4).”
BackgroundInfluentialStates and Situations, Traits and Environments
Asendorpf, J. B., & Rauthmann, J. F. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.007 · Cited by 11
Personality, Preferences and Socioeconomic Behavior
Ferguson, E., Zhao, K., & Smillie, L. D. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.044 · Cited by 9
Latiffianti, E., Ding, Y. C., Sheng, S., et al. (2022) · Wind Energy · doi:10.1002/we.2722 · Cited by 5
“The technique used in the step falls under the broad statistical methodological framework known as causal inference , 11 which originated from social science studies where a natural experiment with observational data, instead of a controlled experiment , needs to be handled.”
Treatment effect optimisation in dynamic environments
Berrevoets, J., Verboven, S., & Verbeke, W. (2022) · Journal of Causal Inference · doi:10.1515/jci-2020-0009 · Cited by 7
Jirsa, V., Petkoski, S., Wang, H., Woodman, M., Fousek, J., Betsch, C., Felgendreff, L., BOHM, R. M., Lilleholt, L., Zettler, I., et al. (2022) · PLOS Digital Health · doi:10.1371/journal.pdig.0000098 · Cited by 6
“infectious spread provides a framework that enables a causal analysis and testing of this hypothesis [10].”
BackgroundOkano, Y., Kase, Y., & Okano, H. (2022) · Stem Cell Reports · doi:10.1016/j.stemcr.2022.10.015 · Cited by 6
Naturalistic Causal Probing for Morpho-Syntax
Amini, A., Pimentel, T., Meister, C., & Cotterell, R. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00554 · Cited by 36
Reasoning-Based Software Testing
Giamattei, L., Pietrantuono, R., & Russo, S. (2023) · IEEE/ACM International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER) · doi:10.1109/icse-nier58687.2023.00018 · Cited by 6
“Pearl introduced the do-operator, a mathematical representation of physical intervention, written as P (Xk|do(Wi = w)) [16].”
BackgroundBias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages
Goldfarb-Tarrant, S., Lopez, A., Blanco, R., & Marcheggiani, D. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.272 · Cited by 21
Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis
Goldfarb-Tarrant, S., Roß, B., & Lopez, A. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.346 · Cited by 19
Isonomy, Austerity, and the Right to Choose Counsel
Moore, J. (2018) · Indiana Law Review · doi:10.18060/4806.1186 · Cited by 5
Modelling Subject Domain Causality for Learning Content Renewal
Gudas, S., Tekutov, J., Butleris, R., & Denisovas, V. (2019) · Informatica · doi:10.15388/informatica.2019.214 · Cited by 5
Bakoyannis, G., Chu, F., Babiker, A. G., & Touloumi, G. (2021) · Japanese Journal of Statistics and Data Science · doi:10.1007/s42081-021-00111-5 · Cited by 5
“We argue that the attenuation in the estimate of treatment effect may not be a bias, but it reflects the difference between the true, conditional and unconditional treatment effects, a phenomenon known as non-collapsibility (Pearl 2009).”
BackgroundSelected Aspects of Interactive Feature Extraction
Grzegorowski, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-662-66544-2_8 · Cited by 6
Self-Efficacy in L2: A Research Proposal
Piechurska-Kuciel, E. (2013) · Second language learning and teaching · doi:10.1007/978-3-319-00161-6_3 · Cited by 13
Design, analysis, and conclusions: Telling a consistent causal story
Harpe, S. E. (2016) · Currents in Pharmacy Teaching and Learning · doi:10.1016/j.cptl.2016.09.001 · Cited by 5
Multi-entity Bayesian network for the handling of uncertainties in SATCOM links
Tian, X. S., Chen, G., Chang, K. C., et al. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2190854 · Cited by 5
“FERENCE SATCOM s s planning a erently enabl smit power) confidence le s that incorpor known SATC ling approach, ork [16].”
BackgroundPedestrians Walking on Reachable Sets and Manifolds
Hartmann, M., & Watzenig, D. (2019) · IEEE International Conference on Mechatronics (ICM) · doi:10.1109/icmech.2019.8722888 · Cited by 5
Fairness Criteria through the Lens of Directed Acyclic Graphs: A Statistical Modeling Perspective
Baer, B. R., Gilbert, D. E., & Wells, M. T. (2020) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780190067397.013.31 · Cited by 15
Covariates and Causal Effects: The Problem of Context
Aliprantis, D. (2013) · Working paper · doi:10.26509/frbc-wp-201310r · Cited by 11
Nabijiang, A. (2020) · Louisiana State University · doi:10.31390/gradschool_theses.5132 · Cited by 7
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.