An introduction to causal inference
- PMID: 20305706
- PMCID: PMC2836213
- DOI: 10.2202/1557-4679.1203
An introduction to causal inference
Abstract
This paper summarizes recent advances in causal inference and underscores 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 underlie 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: those about (1) the effects of potential interventions, (2) probabilities of counterfactuals, and (3) 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. The tools are demonstrated in the analyses of mediation, causes of effects, and probabilities of causation.
Keywords: causal effects; causes of effects; confounding; counterfactuals; graphical methods; mediation; policy evaluation; potential-outcome; structural equation models.
Figures
Similar articles
-
Causal inference based on counterfactuals.BMC Med Res Methodol. 2005 Sep 13;5:28. doi: 10.1186/1471-2288-5-28. BMC Med Res Methodol. 2005. PMID: 16159397 Free PMC article.
-
[Causal analysis approaches in epidemiology].Rev Epidemiol Sante Publique. 2014 Feb;62(1):53-63. doi: 10.1016/j.respe.2013.09.002. Epub 2014 Jan 1. Rev Epidemiol Sante Publique. 2014. PMID: 24388738 French.
-
Counterfactual graphical models for longitudinal mediation analysis with unobserved confounding.Cogn Sci. 2013 Aug;37(6):1011-35. doi: 10.1111/cogs.12058. Epub 2013 Jul 30. Cogn Sci. 2013. PMID: 23899340
-
Mediation analysis methods used in observational research: a scoping review and recommendations.BMC Med Res Methodol. 2021 Oct 25;21(1):226. doi: 10.1186/s12874-021-01426-3. BMC Med Res Methodol. 2021. PMID: 34689754 Free PMC article. Review.
-
Graphical models for causation, and the identification problem.Eval Rev. 2004 Aug;28(4):267-93. doi: 10.1177/0193841X04266432. Eval Rev. 2004. PMID: 15245621 Review.
Cited by
-
On formal limitations of causal ecological networks.Philos Trans R Soc Lond B Biol Sci. 2024 Sep 9;379(1909):20230170. doi: 10.1098/rstb.2023.0170. Epub 2024 Jul 22. Philos Trans R Soc Lond B Biol Sci. 2024. PMID: 39034692
-
From explainable to interpretable deep learning for natural language processing in healthcare: How far from reality?Comput Struct Biotechnol J. 2024 May 9;24:362-373. doi: 10.1016/j.csbj.2024.05.004. eCollection 2024 Dec. Comput Struct Biotechnol J. 2024. PMID: 38800693 Free PMC article. Review.
-
County Mammogram Uptake can be Predicted from Social Determinants of Health, but Patterns Do Not Hold for Individual Patients.Fortune J Health Sci. 2024 Mar;7(1):128-137. doi: 10.26502/fjhs.171. Epub 2024 Feb 17. Fortune J Health Sci. 2024. PMID: 38651007 Free PMC article.
-
Grit was not associated to dropout in Dutch Marine recruits.Mil Psychol. 2022 Mar 2;34(5):616-621. doi: 10.1080/08995605.2022.2028518. eCollection 2022. Mil Psychol. 2022. PMID: 38536348 Free PMC article.
-
A molecular index for biological age identified from the metabolome and senescence-associated secretome in humans.Aging Cell. 2024 Apr;23(4):e14104. doi: 10.1111/acel.14104. Epub 2024 Mar 7. Aging Cell. 2024. PMID: 38454639 Free PMC article.
References
-
- Angrist J, Imbens G, Rubin D. “Identification of causal effects using instrumental variables (with comments),”. Journal of the American Statistical Association. 1996;91:444–472. doi: 10.2307/2291629. - DOI
-
- Arah O.2008“The role of causal reasoning in understanding Simpson’s paradox, Lord’s paradox, and the suppression effect: Covariate selection in the analysis of observational studies,” Emerging Themes in Epidemiology 4doi: 10.1186/1742–7622–5–5, online at <http://www.ete-online.com/content/5/1/5>. - PMC - PubMed
-
- Arjas E, Parner J. “Causal reasoning from longitudinal data,”. Scandinavian Journal of Statistics. 2004;31:171–187. doi: 10.1111/j.1467-9469.2004.02-134.x. - DOI
-
- Avin C, Shpitser I, Pearl J. Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence IJCAI-05. Edinburgh, UK: Morgan-Kaufmann Publishers; 2005. “Identifiability of path-specific effects,”; pp. 357–363.
-
- Balke A, Pearl J. “Counterfactuals and policy analysis in structural models,”. In: Besnard P, Hanks S, editors. Uncertainty in Artificial Intelligence 11. San Francisco: Morgan Kaufmann; 1995. pp. 11–18.
Publication types
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources