The 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.
Causal inference in statistics: An overview
Open accessAbstract
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 301–400 of 2,354
In Support of Clinical Case Reports: A System of Causality Assessment
Kiene, H., Hamre, H. J., & Kienle, G. S. (2013) · Global Advances in Health and Medicine · doi:10.7453/gahmj.2012.061 · Cited by 42
Gil, D., Alfonso‐Iñiguez, S., Pérez‐Rodríguez, L., Muriel, J., & Monclús, R. (2018) · Journal of Evolutionary Biology · doi:10.1111/jeb.13396 · Cited by 47
“telomere length Both for males and females, the DAGs were supported by the data (for females: C = 32.904, df = 28, p = 0.260; for males: C = 7.795, df = 12, p = 0.801).”
MethodInfluentialContrastive Explanations In Neural Networks
Prabhushankar, M., Kwon, G., Temel, D., & AlRegib, G. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190927 · Cited by 47
“Note that these visual causal explanations do not allow causal inference as described by [8].”
BackgroundThe Mediation Formula: A Guide to the Assessment of Causal Pathways in Nonlinear Models
Pearl, J. (2011) · Defense Technical Information Center (DTIC) · doi:10.21236/ada557435 · Cited by 53
Self-citationIntroducing causal inference in the energy-efficient building design process
Chen, X., Abualdenien, J., Singh, M. M., Borrmann, A., & Geyer, P. (2022) · Energy and Buildings · doi:10.1016/j.enbuild.2022.112583 · Cited by 49
“The well-known mantra in statistics, “correlation does not imply causation” [Pearl and Mackenzie, 2018, Aldrich, 1995], remains under-appreciated and rarely discussed in the building design context [Westermann and Evins, 2019, Seyedzadeh et al., 2018].”
BackgroundMethodInfluentialAnderson, B. J., Slater, L. J., Dadson, S., Blum, A. G., & Prosdocimi, I. (2022) · Water Resources Research · doi:10.1029/2021wr030742 · Cited by 44
Optimal fingerprinting under multiple sources of uncertainty
Hannart, A., Ribes, A., & Naveau, P. (2014) · Geophysical Research Letters · doi:10.1002/2013gl058653 · Cited by 44
“We are faced here with the well-known, extensively discussed deficiency of algebraic equations in representing causal relationships, due to the fact that the former are symmetrical objects, whereas the latter are directional ones [Pearl, 2009].”
BackgroundGao, Z., & Mavris, D. N. (2022) · Aerospace · doi:10.3390/aerospace9120750 · Cited by 53
“One can refer to [28,29] for more details on causal inference from a statistics point of view.”
Kim, S., Yoo, H., & Choi, J. (2023) · Sensors · doi:10.3390/s23042265 · Cited by 43
“(ii) Structural causal models framework: SCMs present an easy-to-see relationship of causality [86].”
BackgroundFedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels
Li, J., Li, G., Cheng, H., Liao, Z., & Yu, Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i4.28095 · Cited by 52
Anthropogenic global warming hypothesis: testing its robustness by Granger causality analysis
Triacca, U., Attanasio, A., & Pasini, A. (2013) · Environmetrics · doi:10.1002/env.2210 · Cited by 40
“A more general treatment of causality in statistics is given in Pearl (2009).”
BackgroundOpen versus Endovascular Repair of Ruptured Abdominal Aortic Aneurysms
Speicher, P. J., Barbas, A. S., & Mureebe, L. (2014) · Annals of Vascular Surgery · doi:10.1016/j.avsg.2013.12.025 · Cited by 40
Increased spruce tree growth in Central Europe since 1960s
Cienciala, E., Altman, J., Doležal, J., Kopáček, J., Štěpánek, P., Ståhl, G., & Tumajer, J. (2018) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2017.10.138 · Cited by 42
Hertel, J., Heinken, A., Martinelli, F., & Thiele, I. (2021) · Gut Microbes · doi:10.1080/19490976.2021.1915673 · Cited by 43
Causality Learning: A New Perspective for Interpretable Machine LearningPreprint
Xu, G., Duong, T. D., Li, Q., Liu, S., & Wang, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.16789 · Cited by 97
“Structural causal model [19] consists of two main components: the causal graph and structural equations.”
BackgroundOut-of-Distribution Generalization with Maximal Invariant PredictorPreprint
Koyama, M., & Yamaguchi, S. (2021) · arXiv (Cornell University) · Cited by 46
Liu, S., Xu, J., Wang, R., Fu, X., Liu, X., Zhao, Y., & Zhang, X. (2024) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2024.144626 · Cited by 42
From social media to artificial intelligence: improving research on digital harms in youth
Mansfield, K. L., Ghai, S., Hakman, T., Ballou, N., Vuorre, M., & Przybylski, A. K. (2025) · The Lancet Child & Adolescent Health · doi:10.1016/s2352-4642(24)00332-8 · Cited by 64
Cox, L. A. (2017) · Critical Reviews in Toxicology · doi:10.1080/10408444.2017.1311838 · Cited by 39
“Arrows between variables are absent if they are conditionally independent of each other after conditioning on other variables (e.g. Pearl 2009b; Rottman & Hastie 2014).”
BackgroundMethodInfluentialFairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognition
Sixta, T., Jacques, J. C. S., Buch-Cardona, P., Vazquez, E., & Escalera, S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-65414-6_32 · Cited by 51
“Following the notation from [42], breaking causal links can be expressed by the do() operator, which denotes an intervention on a variable.”
Chen, J., Ho, M., Lee, K., Song, Y., Fang, Y., Goldstein, B. A., He, W., Irony, T., Jiang, Q., van der Laan, M. J., et al. (2021) · Statistics in Biopharmaceutical Research · doi:10.1080/19466315.2021.1883474 · Cited by 45
“, PS) for matching, stratification or weighting; details can be found (e.g., Rubin and Thomas 1996; Greenland, Pearl, and Robins 1999; Rubin 2007; Pearl 2009; Stuart 2010; Hernán and Robins 2016).”
BackgroundMethodAmazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud
Hardt, M., Chen, X., Cheng, X., Donini, M., Gelman, J., Gollaprolu, S., He, J., Larroy, P., Liu, X., McCarthy, N., et al. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467177 · Cited by 77
Emotion prediction as computation over a generative theory of mind
Houlihan, S. D., Max Kleiman-weiner, A., Hewitt, L., Tenenbaum, J. B., & Saxe, R. R. (2023) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2022.0047 · Cited by 76
“In the present work, we focus on prediction, following the stance that forward causal reasoning is a core cognitive capacity that enables explanation and planning [154,155].”
BackgroundWater quality predictions through linear regression - A brute force algorithm approach
Fernandes, A., Fonseca, A., Pacheco, F. A. L., & Fernandes, L. F. S. (2023) · MethodsX · doi:10.1016/j.mex.2023.102153 · Cited by 44
Layout-based Causal Inference for Object Navigation
Zhang, S., Song, X., Li, W., Bai, Y., Yu, X., & Jiang, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01039 · Cited by 41
“[38]) to analyze these navigation works.”
Searching Multiregression Dynamic Models of Resting-State fMRI Networks Using Integer Programming
da Costa, L. C. C., Smith, J. Q., Nichols, T. E., Cussens, J., Duff, E. P., & Makin, T. R. (2015) · Bayesian Analysis · doi:10.1214/14-ba913 · Cited by 39
“Graphical models have been developed in order to define and discover putative causal links between variables (Lauritzen, 1996; Pearl, 2000; Spirtes et al., 2000).”
BackgroundSalimi, B., Parikh, H., Kayali, M., Getoor, L. C., Roy, S., & Suciu, D. M. (2020) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3318464.3389759 · Cited by 46
“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…”
Understanding, Explanation, and Active Inference
Parr, T., & Pezzulo, G. (2021) · Frontiers in Systems Neuroscience · doi:10.3389/fnsys.2021.772641 · Cited by 48
“An influential formalism designed to address causality (Pearl, 2009, 2010) rests upon the idea of interventions.”
BackgroundPublic-Sector Honesty and Corruption: Field Evidence from 40 Countries
Sulitzeanu‐Kenan, R., Tepe, M., & Yair, O. (2021) · Journal of Public Administration Research and Theory · doi:10.1093/jopart/muab033 · Cited by 49
Framework for types of metainferences in mixed methods research
Younas, A., Fàbregues, S., Munce, S., & Creswell, J. W. (2025) · BMC Medical Research Methodology · doi:10.1186/s12874-025-02475-8 · Cited by 69
Momen, M. M., Mehrgardi, A. A., Roudbar, M. A., Kranis, A., Pinto, R. M., Valente, B. D., Morota, G., Rosa, G. J. M., & Daniel Gianola, B. (2018) · Frontiers in Genetics · doi:10.3389/fgene.2018.00455 · Cited by 37
“11 structure could bear information from the joint distribution of all phenotypic traits conditional on 225 their polygenic effects, such that they correct the confounding issues caused by such effects when 226 the traits are genetically correlated [29].”
BackgroundMethodInfluentialExploring the interrelatedness of risk factors for child maltreatment: A network approach
Vial, A., van der Put, C. E., Stams, G. J. J. M., Kossakowski, J. J., & Assink, M. (2020) · Child Abuse & Neglect · doi:10.1016/j.chiabu.2020.104622 · Cited by 58
“In this way, network analyses can meet the critique of Pearl (2009), who stressed that we need to move from traditional statistical analysis to causal analysis.”
BackgroundA user-interactive system for smart thermal environment control in office buildings
Liu, X., Lee, S., Bilionis, I., Karava, P., Joe, J., & Sadeghi, S. A. (2021) · Applied Energy · doi:10.1016/j.apenergy.2021.117005 · Cited by 35
Contribution of animal models toward understanding resting state functional connectivity
Pais‐Roldán, P., Matéo, C., Pan, W., Acland, B. T., Kleinfeld, D., Snyder, L. H., Yu, X., & Keilholz, S. D. (2021) · NeuroImage · doi:10.1016/j.neuroimage.2021.118630 · Cited by 39
“A key challenge is to distinguish causal from non-causal relationships ( Pearl, 2009 ).”
Learning Decomposed Representations for Treatment Effect Estimation
Wu, A., Yuan, J., Kuang, K., Li, B., Wu, R., Zhu, Q., Zhuang, Y. T., & Wu, F. Q. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3150807 · Cited by 97
“l 2 2 all all batch norm False True True False rep normalization True True True False {dR, dy, dt} [7, 4, 1] [5, 4, 1] [7, 7, 3] [2, 5, 5] {hR, hy, ht} [32, 256, 256] [32, 128, 128] [64, 64, 64] [256, 128, 128] {a, b, g, m, } [5, 100, 1, 10, 1e-2] [1e-2, 1, 1e-2, 5, 1e-3] [1e-2, 1e-3, 1e-3, 5, 5] [1e-1, 1, 1, 10, 1]”
MethodAsafo‐Adjei, E., Frimpong, S., Owusu, P., Adam, A. M., Boateng, E., & Abosompim, R. O. (2022) · Complexity · doi:10.1155/2022/6499876 · Cited by 36
“+e information flow theory builds on the philosophy of Dretske [41] and the statistics of Pearl [42].”
Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data
Carilli, M., Gorin, G., Choi, Y., Chari, T., & Pachter, L. S. (2024) · Nature Methods · doi:10.1038/s41592-024-02365-9 · Cited by 40
“The likelihood distributions cannot be obtained solely from the data distributions but require some ‘knowledge of the data-generating process’ 21 .”
Causal Structure Learning and Inference: A Selective Review
Kalisch, M., & Bühlmann, P. (2014) · Quality Technology & Quantitative Management · doi:10.1080/16843703.2014.11673322 · Cited by 50
Farallo, V. R., Muñoz, M. M., Uyeda, J. C., & Miles, D. B. (2020) · Evolution · doi:10.1111/evo.13959 · Cited by 37
“For this reason we did not incorporate temporal components into our remaining analyses, as including these variables would control for the very mechanism EVOLUTION MAY 2020 985 by which the salamander’s microclimatic niche is expressed, namely by behavioral preference (Pearl 2009).”
BackgroundMethodCausal Interventional Training for Image Recognition
Qin, W., Zhang, H., Hong, R., Lim, E., & Sun, Q. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3136717 · Cited by 37
“We highlight that according to Judea Pearl’s causal ladder [17], our interventional level underpins the coun-terfactual level, i.e., the latter requires a well-trained SCM model to infer counterfactuals.”
BackgroundMethodInfluentialWang, J., Grimm, N. B., Lawler, S., & Dong, X. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2218501120 · Cited by 43
Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
Wang, Z., Wei, L., Wang, T., Chen, H., Hao, Y., Wang, X., He, X., & Tian, Q. (2024) · 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/cvpr52733.2024.01630 · Cited by 78
“To address Q1, we separately discuss these questions in few-shot settings in Sec.”
MethodCausal inference for clinicians
Stovitz, S. D., & Shrier, I. (2019) · BMJ Evidence-Based Medicine · doi:10.1136/bmjebm-2018-111069 · Cited by 41
“1 31–33 The decomposition of effects in causal inference 32 34 is a major advancement in the link between evidence and EBM.”
Robert, G., Luo, Q., Yu, T., Chu, C., Ing, A., Jia, T., Orfanos, D. P., Quinlan, E. B., Desrivières, S., Ruggeri, B., et al. (2019) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2019.4063 · Cited by 39
Boers, E., Afzali, M. H., & Conrod, P. (2020) · Preventive Medicine · doi:10.1016/j.ypmed.2020.105992 · Cited by 38
Mannion, A. F., Nauer, S., Arsoy, D., Impellizzeri, F. M., & Leunig, M. (2020) · The Journal of Arthroplasty · doi:10.1016/j.arth.2020.04.090 · Cited by 34
Educational assortative mating and time use in the home.
Miller, R. N. (2020) · Social Science Research · doi:10.1016/j.ssresearch.2020.102440 · Cited by 26
Causal Asymmetry in a Quantum World
Thompson, J., Garner, A. J., Mahoney, J. R., et al. (2018) · eScholarship (California Digital Library) · Cited by 35
Debiasing NLU Models via Causal Intervention and Counterfactual Reasoning
Tian, B., Cao, Y., Zhang, Y., & Xing, C. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i10.21389 · Cited by 56
Economies and Management as A Result of The Fourth Industrial Revolution: An Education Perspective
Shaturaev, J. (2022) · Indonesian Journal of Educational Research and Technology · doi:10.17509/ijert.v3i1.45652 · Cited by 38
“In general, a causal model is a model that depicts causal aspects of a system (Pearl, 2009).”
BackgroundBorrego-Díaz, J., & Galán-Páez, J. (2022) · Minds and Machines · doi:10.1007/s11023-022-09603-z · Cited by 34
“…be necessary to discuss how to enrich these approaches to provide more convincing information from the explainee’s viewpoint (including some representation of causality, if necessary) (Pearl, 2009; van der Waa et al., 2021), or techniques for emergent semantics [(e.g. (Borrego-Díaz & Páez, 2022)].”
BackgroundHow Good Is Good Enough? A Multidimensional, Best-Possible Standard for Research Design
Gerring, J. (2010) · Political Research Quarterly · doi:10.1177/1065912910361221 · Cited by 63
Models and Methods to Identify Peer Effects
An, W. (2014) · SAGE Publications Ltd eBooks · doi:10.4135/9781446294413.n34 · Cited by 56
Targeted learning with daily EHR data
Sofrygin, O., Zhu, Z., Schmittdiel, J. A., Adams, A. S., Grant, R. W., van der Laan, M. J., & Neugebauer, R. (2019) · Statistics in Medicine · doi:10.1002/sim.8164 · Cited by 35
“If the counterfactual outcomes are not explicitly defined based on the more general structural framework through additional explicit assumptions encoded by a causal diagram [30], then an additional consistency assumption is made [47].”
BackgroundDempsey, W., Liao, P., Kumar, S., & Murphy, S. A. (2020) · The Annals of Applied Statistics · doi:10.1214/19-aoas1293 · Cited by 38
“The “fundamental problem of causal inference” [Imbens and Rubin, 2015, Pearl, 2009] is that we can not observe any one of these individual differences.”
Bornkamp, B., & Bermann, G. (2019) · Statistics in Biopharmaceutical Research · doi:10.1080/19466315.2019.1575280 · Cited by 33
“…assumptions under which it is possible to draw causal conclusions in the particular situation discussed above, using the formal language and existing strategies of causal inference developed over the past decades (see, e.g., Pearl 2009; Imbens and Rubin 2015; Hernán and Robins 2018 for reviews).”
BackgroundMayaud, L., Wu, H., Barthélemy, Q., Favennec, P., Delpierre, Y., Congedo, M., Dupeyron, A., & Ritz, M. (2019) · European Spine Journal · doi:10.1007/s00586-019-06051-9 · Cited by 56
“The multivariate time series with 20 temporal observations (for each patient) were analyzed by means of Granger-causality [37] so as to identify which neuromarkers is leading which.”
MethodOptimizing Variational Graph Autoencoder for Community Detection with Dual Optimization
Choong, J. J., Liu, X., & Murata, T. (2020) · Entropy · doi:10.3390/e22020197 · Cited by 38
“Causal inference [15] and Bayesian Deep Learning [16,17] are some examples of attempts to unravel the mysteries behind machine learning algorithms by presenting uncertainties and causal reasons.”
BackgroundQuantifying causality in data science with quasi-experiments
Liu, T., Ungar, L., & Kording, K. P. (2021) · Nature Computational Science · doi:10.1038/s43588-020-00005-8 · Cited by 47
Assessing the Causal Effect of Policies: An Example Using Stochastic Interventions
Diaz, I. M., & van der Laan, M. J. (2013) · The International Journal of Biostatistics · doi:10.1515/ijb-2013-0014 · Cited by 56
Lotfipour, S., Ferguson, E., Leonard, G., Miettunen, J., Perron, M., Pike, G. B., Richer, L., Séguin, J. R., Veillette, S., Jarvelin, M., et al. (2014) · Addiction · doi:10.1111/add.12665 · Cited by 32
“These covariates are selected on theoretical grounds to identify an optimal set that will reduce the possibility of ‘backdoor’ causality [11].”
BackgroundThorson, J. T., Andrews, A. G., Essington, T. E., & Large, S. I. (2024) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.14289 · Cited by 51
“Causal statistics in ecology and other disciplines typically in - volve several steps that define putative causal relationships, esti - mate dependencies among related variables and predict how each variable responds to changes in the others (Bollen & Pearl, 2013; Pearl, 2009a ).”
BackgroundMethodInfluentialPoggiato, G., Andréoletti, J., Pollock, L. J., & Thuiller, W. (2025) · Ecography · doi:10.1111/ecog.07546 · Cited by 40
Interventional Approach for Path-Specific Effects
Lin, S., & VanderWeele, T. J. (2017) · Journal of Causal Inference · doi:10.1515/jci-2015-0027 · Cited by 37
“We make the consistency assumption [3, 5, 25] that Y(a,m1,m2) = Y given A = a, M1 = m1, and M2 = m2.”
BackgroundCausal inference in travel demand modeling (and the lack thereof)
Brathwaite, T., & Walker, J. L. (2017) · Journal of Choice Modelling · doi:10.1016/j.jocm.2017.12.001 · Cited by 46
“not being subjected to change by the policy in question (e.g. walking time between one’s origin and destination). Using this notation5, causal inference focuses on inferring P (Y ijdo(X i = x);Z i) (Pearl, 2009a, Section 3.2.1). Here, x is a particular value of X i. The notation do(X i = x) explicitly denotes the fact…”
BackgroundInfluentialO’Connor, F. K., Thornton, H. R., Ritchie, D., et al. (2019) · International Journal of Sports Physiology and Performance · doi:10.1123/ijspp.2019-0015 · Cited by 33
Cox, L. A. (2020) · Environmental Research · doi:10.1016/j.envres.2020.109638 · Cited by 37
“network risk models (Pearl, 2009; Hack et al., 2010; Cox, 2018b) and dynamic simulation risk models (Cox, 2020) can show how interventions, such as reducing exposure, are predicted to change the probability distributions of outcomes such as disease and mortality risks.”
InfluentialBittmann, F. (2020) · Journal of Happiness Studies · doi:10.1007/s10902-020-00316-7 · Cited by 34
Continuity Scaling: A Rigorous Framework for Detecting and Quantifying Causality Accurately
Xiong, Y., Leng, S., Ma, H., Nie, Q. H., Lai, Y., & Lin, W. J. (2022) · Research · doi:10.34133/2022/9870149 · Cited by 38
“In this work, striving for a comprehensive understanding of causal mechanisms and inspired by the cross-map-based techniques, we develop a mathematically rigorous framework for detecting causality in nonlinear dynamical systems, turning eyes towards investigating the original systems from their cross-maps, which is al…”
BackgroundA causal theory of error scores.
van Bork, R., Rhemtulla, M., Sijtsma, K., & Borsboom, D. (2022) · Psychological Methods · doi:10.1037/met0000521 · Cited by 35
Silva, F., Coward, F., Davies, K., Elliott, S., Jenkins, E. L., Newton, A. C., Riris, P., Linden, M. V., Bates, J., Cantarello, E., et al. (2022) · Sustainability · doi:10.3390/su141610234 · Cited by 55
Ben‐Eliyahu, A., & Zeidner, M. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108264822.041 · Cited by 34
Beyond Econometrics: A Roadmap Towards Financial Machine LearningPreprint
de Prado, M. L. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3365282 · Cited by 46
Lindmark, A., de Luna, X., & Eriksson, M. (2018) · Statistics in Medicine · doi:10.1002/sim.7620 · Cited by 36
Wang, T., Li, H., Su, P., Yu, Y., Sun, X., Liu, Y., Yuan, Z., & Xue, F. (2017) · BMJ Open · doi:10.1136/bmjopen-2016-015640 · Cited by 37
Causal interaction and effect modification: same model, different concepts
Keele, L. J., & Stevenson, R. T. (2020) · Political Science Research and Methods · doi:10.1017/psrm.2020.12 · Cited by 39
“See Pearl (2009), Elwert (2013), and Morgan and Winship (2014) for in-depth reviews of causal graphs.”
BackgroundBlind Identification of Stochastic Block Models from Dynamical Observations
Schaub, M. T., Segarra, S., & Tsitsiklis, J. N. (2020) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 29
Framework for identifying drug repurposing candidates from observational healthcare data
Ozery-Flato, M., Goldschmidt, Y., Shaham, O., Ravid, S., & Yanover, C. (2020) · JAMIA Open · doi:10.1093/jamiaopen/ooaa048 · Cited by 32
“A correct inference of causal effects must involve a subject-matter expert, who is also aware of the data-generation process.(32,33) Our framework allows easy injection of domain knowledge into the implementation of the emulated trials, including: the formulation of cohorts, outcomes and hypothesized confounders.”
BackgroundTyler, S. R., Chun, Y., Ribeiro, V., Grishina, G. T., Grishin, A. V., Hoffman, G. E., Do, A. N., & Bunyavanich, S. (2021) · Cell Reports · doi:10.1016/j.celrep.2021.108975 · Cited by 36
Reinforced Path Reasoning for Counterfactual Explainable Recommendation
Wang, X., Li, Q., Yu, D., Li, Q., & Xu, G. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3354077 · Cited by 45
“With counterfactual explanations, users can understand how minimal changes affect recommendations and conduct counterfactual thinking under the “what-if” scenario [17].”
BackgroundPredictive and prognostic cancer biomarkers revisited
Pritzker, K. P. H. (2015) · Expert Review of Molecular Diagnostics · doi:10.1586/14737159.2015.1063421 · Cited by 33
“The linkages between association and causal inference (biologic mechanism) fostered by Bradford Hill 50 years ago [27] are now formally in development at the intersection of philosophy and mathematics [28].”
BackgroundEmbedding entropy: a nonlinear measure of dynamical causality
Shi, J., Chen, L., & Aihara, K. (2022) · Journal of The Royal Society Interface · doi:10.1098/rsif.2021.0766 · Cited by 31
Bossman, A., Umar, Z., Agyei, S. K., et al. (2022) · Research in Economics · doi:10.1016/j.rie.2022.07.002 · Cited by 31
Equilibrium in the Computing Continuum through Active Inference
Sedlak, B., Pujol, V. C., Donta, P. K., & Dustdar, S. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.05.056 · Cited by 34
“To define a general theory for causality, Pearl [8] proposed Structural Causal Models (SCMs).”
BackgroundWu, Q., Han, J., Yan, Y., Kuo, Y., & Shen, Z. M. (2025) · Health Care Management Science · doi:10.1007/s10729-025-09699-6 · Cited by 65
“They also provided insightful discussions on the topics of causal inference [158] and interpretability [159] of the RL solutions.”
Deconfounding with Networked Observational Data in a Dynamic Environment
Ma, J., Guo, R., Chen, C., Zhang, A., & Li, J. (2021) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3437963.3441818 · Cited by 47
“However, this assumption is often untenable due to the existence of hidden confounders in real-world scenarios [24].”
BackgroundFairness Measures for Machine Learning in Finance
Das, S. R., Donini, M., Gelman, J., Haas, K., Hardt, M., Katzman, J., Kenthapadi, K., Larroy, P., Yilmaz, P., & Zafar, M. B. (2021) · The Journal of Financial Data Science · doi:10.3905/jfds.2021.1.075 · Cited by 60
Causal Intervention for Generalizable Face Anti-Spoofing
Liu, Y., Chen, Y., Dai, W., Li, C., Zou, J., & Xiong, H. (2022) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme52920.2022.9859783 · Cited by 42
“Therefore, to pursue the true causality between X and Y , we leverage the causal intervention [11] P ( Y | do ( x )) instead of the likelihood P ( Y | X ) for the generalizable FAS model.”
BackgroundMethodInfluentialRoumelioti, M., Nolin, T. D., Unruh, M. L., et al. (2016) · PLoS ONE · doi:10.1371/journal.pone.0153157 · Cited by 31
“In these simulations we contrasted the intervention protocols utilized in RCTs of HD patients vis-à-vis RRF as determinants of patient survival.”
MethodInfluentialStatistics and the media: A statistician’s view
McConway, K. J. (2015) · Journalism · doi:10.1177/1464884915593243 · Cited by 31
“…for example in the form of a kind of checklist called the ‘Bradford Hill criteria’ (Hill, 1965), as well as the more recent (and much more complicated and technical) methodology of causal inference (see, for example, Pearl, 2009; Rothman and Greenland, 2005), but they are far from foolproof.”
BackgroundCausal Inference in Accounting ResearchPreprint
Gow, I. D., Larcker, D. F., & Reiss, P. C. (2016) · SSRN Electronic Journal · doi:10.2139/ssrn.2729565 · Cited by 26
“The criterion developed by Pearl (2009b) implies that very different conditioning strategies are needed for each of the causal diagrams (see Appendix A for a more formal treatment).”
BackgroundMethodInfluentialGenerative Counterfactual Introspection for Explainable Deep LearningPreprint
Liu, S., Kailkhura, B., Loveland, D., & Han, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.03077 · Cited by 26
“, they are neither discriminative nor counterfactual [7].”
BackgroundAgyei, S. K., Owusu, P., Bossman, A., et al. (2022) · Discrete Dynamics in Nature and Society · doi:10.1155/2022/3938331 · Cited by 30
“Based on the philosophical principles of Dretske [17] and Pearl’s [18] statistics, the quantification of the intrinsic information flow between two random time series variables is made possible.”
BackgroundIntrinsic drivers of the reputation for CSR: a cognitive analysis of consumer expectations
Ijabadeniyi, A., & Govender, J. P. (2023) · Social Responsibility Journal · doi:10.1108/srj-10-2022-0451 · Cited by 38
Xue, D., Qian, S., & Xu, C. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3398012 · Cited by 43
“The structural causal models (SCMs) [61] abstracted for various methods are illustrated in Fig.”
BackgroundMethodInfluentialCausality, Machine Learning, and Feature Selection: A Survey
Lamsaf, A., Carrilho, R., Neves, J. C., & Proença, H. P. M. C. (2025) · Sensors · doi:10.3390/s25082373 · Cited by 51
“Do-calculus [3], formulated by Judea Pearl, is a theoretical framework that allows researchers to determine the effects of interventions in causal inference models.”
Advancing causal inference in ecology: Pathways for biodiversity change detection and attribution
Schrodt, F., Beck, M., Estopinan, J., Bowler, D. E., Fontaine, C., Gaüzère, P., Goury, R., Grenié, M., Martins, I. S., Morueta‐Holme, N., et al. (2025) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.70131 · Cited by 55
“Using the classic definition by Pearl ( 2009 ), ‘a causal relationship exists when variation in an independent variable leads to, or causes, variation in a dependent variable, and this relationship is not spurious or confounded by other variables’.”
Are Women Happier When Their Spouse is Teleworker?
Gıovanıs, E. (2017) · Journal of Happiness Studies · doi:10.1007/s10902-017-9847-0 · Cited by 39
Realising stratified psychiatry using multidimensional signatures and trajectories
Joyce, D. W., Kehagia, A. A., Tracy, D. K., Proctor, J., & Shergill, S. S. (2017) · Journal of Translational Medicine · doi:10.1186/s12967-016-1116-1 · Cited by 33
“The choice of criteria varies depending on the intended use of the algorithm and the definition of ‘associational’ versus ‘causal’ [120, 121].”
BackgroundDing, C., Pu, F., Li, C., Xu, X., Zou, T., & Li, X. (2020) · Water · doi:10.3390/w12092372 · Cited by 31
“Under the potential outcome framework [40], the changing variable is referred to as ”treatment” and the corresponding response as ”outcome”.”
Background
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.