Potential Outcome and Directed Acyclic Graph Approaches to Causality: Relevance for Empirical Practice in Economics

2019/07/16 by Guido W. Imbens, Imbens, Guido W. · 3 voices
Arts and Humanities · Computer Science · Decision Sciences · Mathematics · Social Sciences · #Advanced Causal Inference Techniques #Bayesian Modeling and Causal Inference #Decision-Making and Behavioral Economics #Game Theory and Applications #Philosophy and History of Science #Qualitative Comparative Analysis Research #stat.ME

paper · pdf · doi:10.48550/arxiv.1907.07271

openalex publication_date 2019/07/16 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28

Abstract

In this essay I discuss potential outcome and graphical approaches to causality, and their relevance for empirical work in economics. I review some of the work on directed acyclic graphs, including the recent "The Book of Why," by Pearl and MacKenzie. I also discuss the potential outcome framework developed by Rubin and coauthors, building on work by Neyman. I then discuss the relative merits of these approaches for empirical work in economics, focusing on the questions each answer well, and why much of the the work in economics is closer in spirit to the potential outcome framework.

Discussions

• You can’t really do a proper DAG for DiD since it relies on a functional form restriction (additive confounding) which DAGs are explicitly agnostic about. I always liked this Imbens piece on the limit [bsky, 25 points, 3 comments]
• In 2019, I posted this tweet, which was later cited by Guido Imbens in his 'DAGs vs. PO' paper, published in JEL (arxiv.org/pdf/1907.07271). Fast forward to today, and I came across an interesting p [bsky, 8 points, 0 comments]
• DAGs are a more recent introduction to econometrics, though with some very old precedent, so they haven't made it into most textbooks and teaching materials. Also, many econometricians dislike or are [bsky, 2 points, 1 comments]

Related

• Potential Outcome and Directed Acyclic Graph Approaches to Causality: Relevance for Empirical Practice in Economics
• Causal Inference: A Tale of Three Frameworks
• Potential Outcomes and Decision Theoretic Foundations for Statistical Causality: Response to Richardson and Robins
• Potential Outcome and Decision Theoretic Foundations for Statistical Causality
• Complementary strengths of the Neyman-Rubin and graphical causal frameworks