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 901–1,000 of 2,354
Robust Event Forecasting with Spatiotemporal Confounder Learning
Deng, S., Rangwala, H., & Ning, Y. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539427 · Cited by 15
“Hidden confounders are common in real-world observational data [30].”
BackgroundCausal effect analysis-based intrusion detection system for IoT applications
Bhaskara, S., & Rathore, S. S. (2023) · International Journal of Information Security · doi:10.1007/s10207-023-00674-2 · Cited by 12
“Themaindifferencebetween causal inference and correlation inference is that the former analyzes the response of the effect variable when the cause is changed [48,49].”
Background30 Years of Rough Sets and Future Perspectives
Skowron, A., Jankowski, A. W., & Świniarski, R. W. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41218-9_1 · Cited by 10
“and another view by Judea Pearl (the 2011 winner of the ACM Turing Award, “for fundamental contributions to artificial intelligence through the development of a calculus for probabilistic and causal reasoning”) [14]:”
BackgroundProving the performance of a new revenue management system
Talluri, K. T., Castejon, F., Codina, B., & Magaz, J. (2010) · Journal of Revenue and Pricing Management · doi:10.1057/rpm.2010.19 · Cited by 10
Wang, T., Sun, J., Zhang, W., & Yuan, J. (2013) · Process Biochemistry · doi:10.1016/j.procbio.2013.11.003 · Cited by 9
Sparse Instrumental Variables (SPIV) for Genome-Wide Studies
McKeigue, P., Krohn, J. P., Storkey, A., & Agakov, F. V. (2010) · neural information processing systems · Cited by 9
Similarity, kernels, and the fundamental constraints on cognition
Shahbazi, R., Raizada, R. D. S., & Edelman, S. (2016) · Journal of Mathematical Psychology · doi:10.1016/j.jmp.2015.11.004 · Cited by 9
“suffice (Pearl, 2009; Steyvers, Tenenbaum,Wagenmakers, & Blum, 2003).”
BackgroundUsing network analysis to study behavioural phenotypes: an example using domestic dogs
Goold, C. M., Vas, J., Olsen, C., & Newberry, R. C. (2016) · Royal Society Open Science · doi:10.1098/rsos.160268 · Cited by 8
Knick, S. T., Hanser, S. E., Grace, J. B., Hollenbeck, J. P., & Leu, M. (2017) · Forest Ecology and Management · doi:10.1016/j.foreco.2017.06.017 · Cited by 9
Sparse probit linear mixed model
Mandt, S., Wenzel, F., Nakajima, S., Cunningham, J. P., Lippert, C., & Kloft, M. (2017) · Machine Learning · doi:10.1007/s10994-017-5652-6 · Cited by 11
“When it is unobserved, it induces spurious correlations that have no causal interpretation:we say that the genotypes and traits are confounded (Imbens and Rubin 2015; Pearl 2009; Morgan and Winship 2014).”
BackgroundGranular Games in Real-Time Environment
Świechowski, M., & Ślȩzak, D. (2018) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2018.00074 · Cited by 8
“For instance, let us refer to [29]: Causal inference requires two additional ingre-”
BackgroundDirect and Indirect Effects—An Information Theoretic Perspective
Schamberg, G., Chapman, W. E., Xie, S., & Coleman, T. P. (2020) · Entropy · doi:10.3390/e22080854 · Cited by 10
“those summarized by [49]) or information theoretic (IT) (i.”
BackgroundDing, H., An, N., Au, R., Devine, S., Auerbach, S. H., Massaro, J. M., Joshi, P. S., Liu, X., Liu, Y., Mahon, E., et al. (2020) · Journal of Medical Internet Research · doi:10.2196/15376 · Cited by 10
“It can summarize a complex system into a simplified representation to capture the hierarchical interplay among components and provide insights on how each component influences others [27].”
BackgroundJabbari, F., & Cooper, G. F. (2020) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611976236.49 · Cited by 14
“Causal Bayesian networks (CBNs) have been used extensively for discovering causal knowledge from observational data [16, 20].”
BackgroundErgonomics for indoor air environments: Problems, reflections and investigations
Mo, J., Cao, B., Liu, N., Sun, Z., Xu, Y., Zhu, Y., & Zhang, Y. (2022) · Chinese Science Bulletin (Chinese Version) · doi:10.1360/tb-2022-0019 · Cited by 11
Case Selection and Causal Inference in Qualitative ResearchPreprint
Plümper, T., Troeger, V. E., & Neumayer, E. (2010) · SSRN Electronic Journal · doi:10.2139/ssrn.1439868 · Cited by 8
Nieuwenhuis, R. (2013) · doi:10.3990/1.9789036535823 · Cited by 9
Introduction to the Special Issue on Propensity Score Methods in Behavioral Research
Pruzek, R. M. (2011) · Multivariate Behavioral Research · doi:10.1080/00273171.2011.576618 · Cited by 9
“His basic approach, which is strongly connected to structural equation modeling, is fundamental as well as comprehensive; his recent review (Pearl, 2009) should also be noted.”
South, S. C., Reichborn‐Kjennerud, T., Eaton, N. R., & Krueger, R. F. (2012) · Wiley eBooks · doi:10.1002/9781118133880.hop205001 · Cited by 9
Chakrabortty, A., Nandy, P., & Li, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.10652 · Cited by 26
“This can be denoted by Pearl’s do-operator: do(Xi = xi) [Pearl, 2009], which corresponds to removing the edges into Xi in G0 (or equivalently, setting the i-th column of BG0 equal to zero) and replacing i by the constant xi.”
BackgroundWalker, J. A. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/133785 · Cited by 9
“…explanatory models, a modeled coefficient is a consistent estimate of the causal parameter βj only if the statistical model correctly identifies the causal structure and does not exclude confounding variables, or if the statistical model uses well-known methods to block confounders (Pearl, 2009a).”
BackgroundMethodCausality and Batch Reinforcement Learning: Complementary Approaches To Planning In Unknown DomainsPreprint
Bannon, J., Windsor, B., Song, W., & Li, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.02579 · Cited by 22
“A line of research in computer science that grew out of approaches in economics (Duncan, 2014; Goldberger, 1973) and graphical models (Neapolitan et al., 2004) culminated in the formalization of structural causal models (SCM) (Pearl et al., 2009).”
BackgroundEstimating Networks of Sustainable Development GoalsPreprint
Ospina-Forero, L., Ramos, G. C., & Guerrero, O. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3385362 · Cited by 9
“In their most general form [37,41], they can be characterized in terms of “parent-child” relations between variables and noise terms.”
BackgroundKaakinen, M. (2012) · Cited by 8
Giardini, F., Hadjidimitriou, N. S., Mamei, M., Bastardi, G., Codeluppi, N., & Pancotto, F. (2023) · Scientific Reports · doi:10.1038/s41598-023-48130-4 · Cited by 10
Instrumental Variable Learning for Chest X-ray Classification
Nie, W., Zhang, C., Song, D., Bai, Y., Xie, K., & Liu, A.-A. (2023) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53992.2023.10394601 · Cited by 15
“Causal inference [19] is a powerful methodology that can be applied to numerous domains, including statistics [8] and epidemiology [20].”
Liu, J., & Li, D. M. (2024) · Asian Journal of Criminology · doi:10.1007/s11417-024-09429-x · Cited by 21
“More precise post-hoc inferences fortify our ability to evaluate algorithmic fairness, both from input and output perspectives (Pearl, 2009).”
Weerdt, D. D., Simons, M., Struyf, E., & Tack, H. (2024) · Review of Educational Research · doi:10.3102/00346543241262807 · Cited by 22
“An important feature of scientific research is the identification of cause-effect relationships among variables ( J.Pearl, 2009).”
Li, Y., Scheel‐Sailer, A., Riener, R., & GRANADOS, D. F. P. (2024) · Scientific Reports · doi:10.1038/s41598-024-75691-9 · Cited by 12
“Controlled intervention experiments are necessary to evaluate and validate the causal inference using the learned causal graph 41 , especially in the absence of ground truth.”
Understanding complex systems through differential causal networks
Defilippo, A., Giorgi, F. M., Veltri, P., & Guzzi, P. H. (2024) · Scientific Reports · doi:10.1038/s41598-024-78606-w · Cited by 10
Causality-driven sequence segmentation assisted soft sensing for multiphase industrial processes
He, Y., Zhang, X., Kong, X., Yao, L., & Song, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129612 · Cited by 10
Causal network inference based on cross-validation predictability
Zhang, Y., Li, Q., Wang, J., Chang, X., Chen, L., & Liu, X. (2025) · Communications Physics · doi:10.1038/s42005-025-02091-4 · Cited by 13
“In contrast, Bayesian network and structural causal model (SCM) ( 23-25 ) are able to handle time independent data based on statistical independence and intervention (e.g. do-calculus do-calculus operation), and can identify the directed causal relations between molecules.”
Disentangled Knowledge Tracing for Alleviating Cognitive Bias
Zhou, Y., Lv, Z., Zhang, S., & Chen, J. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714607 · Cited by 37
“The key to the counterfactual is to intervene causally on 𝑆 , also called the do-operator [50, 52, 72], i.e. , 𝑑𝑜 ( 𝑆 = 𝑠 ∗ ) forcibly cuts off the edge 𝐷 → 𝑆 in Figure 2(a), replaces 𝑠 in Eq.”
Yang, L., Gao, C., Qin, R., Wu, Q., Sun, H., & Zhang, T. (2025) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2025.138831 · Cited by 9
Visual Representation Learning through Causal Intervention for Controllable Image Editing
Huang, S., Li, H., Zheng, C., Wang, L., Liao, G., Gong, Z., Yang, H., & Liu, L. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02187 · Cited by 9
“Therefore, we follow the paradigm of [19, 23] and exploit the causal intervention to separate the direct causal effect from the effect of confounding biases.”
Performative Prediction: Past and Future
Hardt, M., & Mendler-Dünner, C. (2025) · Statistical Science · doi:10.1214/25-sts986 · Cited by 105
Compound coastal marine–terrestrial heatwaves associated with humid-heat stress in Europe
Barkhordarian, A., Brunet, E., & Baehr, J. (2025) · Scientific Reports · doi:10.1038/s41598-025-32049-z · Cited by 8
“In essence, FAR quantifies the degree to which GHG forcing can be considered a necessary driver of the extreme events 74,75 .”
Mendelian Randomization Methods for Causal Inference: Estimands, Identification and Inference
Yao, M., Wang, A., Li, X., & Liu, Z. (2026) · Statistics in Medicine · doi:10.1002/sim.70394 · Cited by 15
Approach–Avoidance Theories of Personality
Corr, P. J., & Krupıć, D. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.025 · Cited by 15
García‐Baquero, G., Odriozola, I., & Aldezábal, A. (2020) · Agronomy · doi:10.3390/agronomy11010025 · Cited by 10
Causal Analysis of Customer Churn Using Deep Learning
Rudd, D. H., Huo, H., & Xu, G. (2021) · International Conference on Digital Society and Intelligent Systems (DSInS) · doi:10.1109/dsins54396.2021.9670561 · Cited by 15
“Recent causal inference developments highlight fundamental alterations required to move from standard statistical analysis towards multivariate causal analysis [3].”
BackgroundLeveraging change point detection to discover natural experiments in data
He, Y., Burghardt, K., & Lerman, K. (2022) · EPJ Data Science · doi:10.1140/epjds/s13688-022-00361-7 · Cited by 13
“To address this challenge, researchers are developing causal inference methods to quantify the effects of actions within heterogeneous observational data [2–5].”
Observational process data analytics using causal inference
Yang, S., & Bequette, B. W. (2022) · AIChE Journal · doi:10.1002/aic.17986 · Cited by 13
Albers, P. N., Rinaldi, C., Brown, H., Mason, K., d’Apice, K., McGill, E., McQuire, C., Craig, P., Laverty, A. A., Beeson, M., et al. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2023.1192055 · Cited by 13
Improving interventional causal predictions in regulatory risk assessment
Cox, L. A. (2023) · Critical Reviews in Toxicology · doi:10.1080/10408444.2023.2229923 · Cited by 8
“These are interventional causal predictions (Pearl 2009): they predict percentage reductions in mortality risks that would be caused by different counterfactual reductions in fine particulate (PM2.”
BackgroundMethodInfluentialVariable Importance Without Impossible Data
Mase, M., Owen, A. B., & Seiler, B. B. (2023) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-040722-045325 · Cited by 18
Data-driven detection of critical points of phase transitions in complex systems
Tao, P., Du, C., Xiao, Y., & Zeng, C. (2023) · Communications Physics · doi:10.1038/s42005-023-01429-0 · Cited by 10
Predicting and optimizing marketing performance in dynamic markets
Guhl, D., Paetz, F., Wagner, U., & Wedel, M. (2024) · OR Spectrum · doi:10.1007/s00291-024-00755-1 · Cited by 16
Liu, Q., Chen, Z., & Wong, W. H. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2322376121 · Cited by 27
Rotari, M., & Külahçı, M. (2024) · Quality Engineering · doi:10.1080/08982112.2024.2372489 · Cited by 8
“Judea Pearl made substantial contributions to promoting DAGs in causal inference (Pearl 2009a, 2009b).”
Heterogeneous returns and the persistence of agricultural technology adoption
Zeitlin, A. D., Caria, S. A., Dzene, R., Jánský, P., Opoku, E., & Teal, F. (2010) · Oxford University Research Archive (ORA) (University of Oxford) · Cited by 11
Kaakinen, M., Sovio, U., Hartikainen, A., Pouta, A. M., Savolainen, M. J., Herzig, K., Elliott, P., Stavola, B. L. D., Läärä, E., & Järvelin, M. (2014) · Journal of Epidemiology & Community Health · doi:10.1136/jech-2013-203661 · Cited by 12
Magrini, A., Blasi, S., & Stefanini, F. M. (2017) · Biometrical Letters · doi:10.1515/bile-2017-0002 · Cited by 8
“…domain on the real numbers or qualitative with a finite number of values, and is composed of: 1. a qualitative part, encoded by a directed acyclic graph (DAG: Lauritzen, 1999), showing the factorization of the joint probability distribution of variables in 𝑿: 𝑃(𝑿) = ∑ 𝑃(𝑋𝑗|…”
Communicating more clearly about deaths caused by air pollution
Cox, L. A. (2019) · Global Epidemiology · doi:10.1016/j.gloepi.2019.100003 · Cited by 9
Causal inference and American political development: contrasts and complementarities
Caughey, D., & Chatfield, S. (2019) · Public Choice · doi:10.1007/s11127-019-00694-4 · Cited by 10
Jenkins, L. C., Chang, W., Buscemi, V., Cunningham, C. N., Cashin, A. G., McAuley, J. H., Liston, M. B., & Schabrun, S. M. (2019) · BMJ Open · doi:10.1136/bmjopen-2019-035792 · Cited by 8
Bayesian belief network modelling of household food security in rural South Africa
Eyre, R. W., House, T., Gómez-Olivé, F. X., & Griffiths, F. E. (2021) · BMC Public Health · doi:10.1186/s12889-021-10938-y · Cited by 10
“Our models are still much more suitable for causally modelling the system, as they have the directional structure that is necessary in order to do so [48].”
MethodCausal-Aware Generative Imputation for Automated Underwriting
Li, Q., Duong, T. D., Wang, Z., et al. (2021) · Proceedings of the ... ACM International Conference on Information & Knowledge Management · doi:10.1145/3459637.3481900 · Cited by 8
“Following the causality analysis theory [18, 24], we assume that latent confounder U is the always parent node of the features ({vo }, {vp }).”
MethodOn some fundamental challenges in monitoring epidemics
Vasiliauskaitė, V., Antulov-Fantulin, N., & Helbing, D. (2021) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2021.0117 · Cited by 10
“For recent advances in causal inference see [7].”
BackgroundNaser, M. Z., & Ross, B. E. (2022) · Civil Engineering and Environmental Systems · doi:10.1080/10286608.2022.2049257 · Cited by 8
“Remember that explainability methods may not reveal hidden or mechanistic causality as proper causal AI models (Pearl 2009).”
Bingham, N., & Krzanowski, W. (2022) · British Journal for the History of Mathematics · doi:10.1080/26375451.2022.2045811 · Cited by 8
“For later views, see (Dawid 1979), (Cox and Wermuth 2004), (Pearl 2009a, 2009b).”
Tai, A., Lin, P.-H., Huang, Y., & Lin, S. (2022) · Statistical Methods in Medical Research · doi:10.1177/09622802221104239 · Cited by 8
Intervention & Interaction Federated Abnormality Detection with Noisy Clients
Liu, X., Li, W., & Yuan, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16452-1_30 · Cited by 16
Chen, X., Wang, S., Qi, L., Li, Y., & Yao, L. (2023) · World Wide Web · doi:10.1007/s11280-023-01187-7 · Cited by 13
“Structural Causal Models (SCMs) [19] can be represented as a tuple: Mt (Vt ,Ut , F) with the following components based on the state and action composition form at timestamp t .”
BackgroundAutomated interviews on clinical case reports to elicit directed acyclic graphs
Luciani, D., & Stefanini, F. M. (2011) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2011.11.007 · Cited by 8
Using Causal Models to Manage the Cyber Threat to C2 Agility: Working with the Benefit of Hindsight
Barnett, A. G., Smith, S., & Whittington, R. P. (2014) · Cited by 8
Classical Statistics and Statistical Learning in Imaging Neuroscience
Bzdok, D. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00543 · Cited by 170
“statistical learning might give rise to different categories of inference, which remains an inherently difficult concept to define (Chamberlin, 1890; Pearl, 2009; Platt, 1964).”
BackgroundCOLOGNE, J. B. (2013) · Health Physics · doi:10.1097/hp.0b013e31828388ea · Cited by 8
Caprara, G. V., & Vecchione, M. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.038 · Cited by 9
Martín‐Raugh, M. P., Williams, K. M., & Lentini, J. E. (2020) · ETS Research Report Series · doi:10.1002/ets2.12306 · Cited by 14
Exploratory Causal Analysis with Time Series Data
McCracken, J. M. (2016) · Synthesis lectures on data mining and knowledge discovery · doi:10.1007/978-3-031-01909-8 · Cited by 7
Data Generating Process to Evaluate Causal Discovery Techniques for Time Series DataPreprint
Lawrence, A. R., Kaiser, M., Sampaio, R., & Sipos, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.08043 · Cited by 24
“We propose a flexible, yet easy to use synthetic data generation process based on structural causal models [23], which can be used to benchmark causal discovery methods under a wide-range of conditions.”
MethodCausal inference for process understanding in Earth sciencesPreprint
Massmann, A. K., Gentine, P., & Runge, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.00912 · Cited by 25
“…there are other identification strategies like the front door criterion [see Section 3.5.2 in Pearl, 2009b] and instrumental variables [see Chapter 8 in Pearl, 2009b] that do not rely on observing variables along the backdoor path, and can be used in some cases where observations are not available…”
BackgroundMethodInfluentialLanguage bias in Visual Question Answering: A Survey and TaxonomyPreprint
Yuan, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.08531 · Cited by 23
Statistical Methods in Epidemiology
Ng, H. K. T., & Lovrić, M. (2025) · Springer eBooks · doi:10.1007/978-3-662-69359-9_616 · Cited by 10
Best practices for moving from correlation to causation in ecological research
Correia, H., Dee, L. E., Byrnes, J. E. K., Fieberg, J., Fortin, M., Glymour, C., Runge, J., Shipley, B., Shpitser, I., Siegel, K., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-69878-z · Cited by 25
“The formalization of these assumptions is one of the most important sci-enti fi c advances for answering causal questions 26,28,58 .”
InfluentialCLadder: Assessing Causal Reasoning in Language Models
Jin, Z., Chen, Y., Leeb, F., Gresele, L., Kamal, O., Lyu, Z., Blin, K., Adauto, F. G., Kleiman-Weiner, M., Sachan, M., et al. (2023) · arXiv · doi:10.48550/arxiv.2312.04350 · Cited by 8
Kamal, K., & Farooq, B. (2023) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981231152246 · Cited by 7
“Based on the potential outcome concept, the prediction of each policy effect is equal to the difference of an average outcome between the treatment and control groups (23).”
BackgroundChen, D., Petersen, M. L., Rytgaard, H. C. W., Grøn, R., Lange, T., Rasmussen, S., Pratley, R. E., Marso, S. P., Kvist, K., Buse, J. B., et al. (2023) · Statistics in Biopharmaceutical Research · doi:10.1080/19466315.2023.2173644 · Cited by 13
Explainability and causality for robust, fair, and trustworthy artificial reasoning
Rawal, A., Raglin, A. J., Sadler, B. M., & Rawat, D. B. (2023) · Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications · doi:10.1117/12.2666085 · Cited by 7
“6,7,10,11 Causal graphs describe the causal effects between the different variables.”
BackgroundFrom Effects of Governance to Causes of Epistemic Change
Gläser, J. (2024) · Minerva · doi:10.1007/s11024-024-09526-2 · Cited by 12
“This is achieved by finding associations among variables through statistical analysis and providing grounds on which this correlation can be considered to represent causation (Pearl 2009).”
Population and community ecology: past progress and future directions
Krebs, C. J., Boutin, S. A., & Boonstra, R. (2024) · Integrative Zoology · doi:10.1111/1749-4877.12863 · Cited by 13
“There is a very large literature on cause and effect that is important for all the sciences to link to the philosophical literature about causality and the very general issue of what we mean by evidence in science (Platt 1964; Pearl 2009; Sugihara et al. 2012; Kimmel et al. 2021; Hone & Krebs 2023).”
Nasir, M., Summerfield, N. S., Simsek, S., & Oztekin, A. (2024) · Decision Sciences · doi:10.1111/deci.12642 · Cited by 8
Wu, Y., MARKHAM, A. F., Wang, L., et al. (2024) · Journal of Public Transportation · doi:10.1016/j.jpubtr.2024.100114 · Cited by 7
Advances in Projection Predictive Inference
McLatchie, Y., Rögnvaldsson, S., Weber, F., & Vehtari, A. (2025) · Statistical Science · doi:10.1214/24-sts949 · Cited by 26
“This is done by including in the model what Pearl (2009) calls the admissible set of predictors.”
MethodStructure Causal Models and LLMs Integration in Medical Visual Question Answering
Xu, Z., Li, Q., Nie, W., Wang, W., & Liu, A.-A. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3564320 · Cited by 22
“The purpose of causal inference [13] is to pursue causal effects and eliminate false biases [22].”
InfluentialCapturing the emergent dynamical structure in biophysical neural models
Milinkovic, B., Barnett, L., Carter, O. L., Seth, A. K., & Andrillon, T. (2025) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1012572 · Cited by 9
“This approach can be applied even without interventionist methods of causality [96,97], extending across various bidirectional networks [75,98].”
Park, M., Lee, K. H., Chun, J., & Kim, J. (2025) · Journal of Affective Disorders · doi:10.1016/j.jad.2025.119496 · Cited by 9
Missing data in ecology: Syntheses, clarifications, and considerations
Dumelle, M., Trangucci, R., Nahlik, A. M., Olsen, A. R., Irvine, K. M., Blocksom, K. A., Hoef, J. M. V., & Fuentes, C. (2025) · Ecological Monographs · doi:10.1002/ecm.70037 · Cited by 13
Economic Experiments in Recreational Fishing Studies
van Putten, I. E., Trudeau, A., Mackay, M., Obregón, C., Post, J. R., Richter, A. P., Schuch, E., & Solomon, C. T. (2025) · Fish & fisheries series/Fish and fisheries series (Print) · doi:10.1007/978-3-031-99739-6_14 · Cited by 7
Discovering shakers from evolving entities via cascading graph inference
Shi, X., Fan, W., Zhang, J., et al. (2011) · ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2020408.2020570 · Cited by 7
“, [27, 10, 23]).”
Frameworks for Credible Causal Inference in Observational Studies of Family Violence
Rose, R. A. (2018) · Journal of Family Violence · doi:10.1007/s10896-018-0011-3 · Cited by 7
“Secondly, as previously noted, the framework has been criticized for not being a self-contained model for describing causal relationships (Pearl 2000).”
MethodSpectral Partitioning of Time-varying Networks with Unobserved Edges
Schaub, M. T., Segarra, S., & Wai, H.-T. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682815 · Cited by 7
“A number of notions for network inference have featured in the literature, ranging from estimating ‘functional’ couplings based on statistical association measures such as correlation or mutual information [7], all the way to causal inference [8].”
BackgroundVariant Approach for Identifying Spurious Relations That Deep Learning Models Learn
Tesch, T., Kollet, S. J., & Garcke, J. (2021) · Frontiers in Water · doi:10.3389/frwa.2021.745563 · Cited by 8
“A similar concept to ours has, to the best of our knowledge, only been pursued systematically in a strict causality framework [for details on this framework see e.g., Pearl, 2009 or for a more methodological focus (Guo et al., 2020)].”
MethodNaser, M. Z. (2022) · AI in Civil Engineering · doi:10.1007/s43503-022-00005-9 · Cited by 12
“(Imbens, 2020; Pearl, 2009).”
BackgroundEvaluation and projections of the East Asian summer monsoon in a perturbed parameter ensemble
Rostron, J. W., Sexton, D. M. H., Furtado, K., Carvalho, M. J., Milton, S. F., Rodríguez, J. M., & Zhang, W. (2022) · Climate Dynamics · doi:10.1007/s00382-022-06507-7 · Cited by 11
Mixed messages: most spinal pain and osteoarthritis observational research is unclear or misaligned
Gleadhill, C. P., Lee, H., Kamper, S. J., Cashin, A. G., Hansford, H. J., Traeger, A. C., da Silva, P. V., Nolan, E., Davidson, S. R. E., Wilczynska, M., et al. (2023) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2023.01.005 · Cited by 7
Johnson, B., Bartola, J., Angell, R., Witty, S., Giguere, S., & Brun, Y. (2023) · EURO Journal on Decision Processes · doi:10.1016/j.ejdp.2023.100031 · Cited by 24
Xiang, S., Xu, D., Jin, Y., Wang, R., Wen, C., & Ding, X. (2023) · Inflammopharmacology · doi:10.1007/s10787-023-01241-w · Cited by 9
“Chain and Fork are the basic connecting structures of the causal diagram, which can intuitively express causal hypotheses (Pearl and Judea 2009).”
BackgroundConditional average treatment effect estimation with marginally constrained models
van Amsterdam, W. A. C., & Ranganath, R. (2023) · Journal of Causal Inference · doi:10.1515/jci-2022-0027 · Cited by 7
“:3) encompasses all conditional distributions on × 0, 1 { } , i.e. in the non-parametric estimation setting, it follows that ∃ ∗ ∈ g For more details on these assumptions, see e.g. [24,25].”
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.