Donald Rubin

Overview

Donald B. Rubin is John L. Loeb Professor Emeritus of Statistics at Harvard University. He is one of the most influential statisticians of the 20th century, credited with formalizing the potential outcomes framework for causal inference — now called the Rubin Causal Model (RCM) — which is the foundational language of modern causal inference in statistics, economics, epidemiology, and social science. He also made landmark contributions to propensity score methods (with Rosenbaum), missing data theory, and multiple imputation.

Key Contributions / Features

• Rubin Causal Model (RCM) — potential outcomes framework for causal inference (1974 JEP; 1978 AoS); every unit has a potential outcome Y(d) under each treatment d, and the causal effect is their comparison; only one is ever observed (the fundamental problem of causal inference)
• SUTVA — Stable Unit Treatment Value Assumption (Rubin 1978/1980): no interference between units and no hidden treatment versions; the foundational assumption permitting unit-level potential outcome notation
• Propensity score — with Rosenbaum (Biometrika 1983), showed that conditioning on P(T=1|X) removes all observed confounding; enabled matching, weighting, and stratification methods that are now standard
• Missing data — developed the formal framework (missing completely at random, missing at random, not missing at random) and multiple imputation methods that became the standard approach to incomplete data in applied research
• AIR (1996) framework — with Angrist and Imbens (JASA 1996), embedded IV within the RCM; formalized the compliance typology and the LATE identification result; made IV assumptions interpretable in potential-outcomes terms

Related

• Rubin Causal Model
• Instrumental Variables
• Local Average Treatment Effect
• Guido Imbens
• Joshua Angrist

Sources

• Angrist Imbens and Rubin 1996 — Identification of Causal Effects Using Instrumental Variables
• Angrist Imbens and Rubin 1996 — Identification of Causal Effects Using Instrumental Variables Rejoinder
• Heckman 1996 — Identification of Causal Effects Using Instrumental Variables Comment
• Heckman 2008 — Econometric Causality
• Meyer 1995 — Natural and Quasi-Experiments in Economics
• Moffitt 2005 — Remarks on the Analysis of Causal Relationships in Population Research
• Robins and Greenland 1996 — Identification of Causal Effects Using Instrumental Variables Comment