Sander Greenland

Overview

Sander Greenland is Professor Emeritus of Epidemiology at the UCLA Fielding School of Public Health. He is a leading methodologist in epidemiologic causal inference, confounding theory, bias analysis, and Bayesian approaches to observational studies. With Robins, he co-developed approaches to causal inference under noncompliance and time-varying treatments. His earlier work with Robins on identifiability and confounding (Greenland and Robins 1986) established the epidemiological vocabulary for the exchangeability conditions that underpin causal inference in observational data.

Key Contributions / Features

• Greenland and Robins (1986) — "Identifiability, Exchangeability, and Epidemiological Confounding." International Journal of Epidemiology 15(3): 413–419. Formalized the concept of exchangeability as the causal condition for unconfoundedness in epidemiology — the epidemiological analogue of ignorable assignment.
• Robins and Greenland (1996) — Comment on AIR (1996); argued for ATE over LATE as the public health parameter of interest; derived Robins-Manski bounds and SNMM-based identification; showed LATE is not identified in bioequivalence trials.
• Bias analysis — Developed systematic frameworks for quantifying and propagating sources of systematic error (confounding, selection bias, information bias) in epidemiological studies, including probabilistic bias analysis and multiple bias modeling.

Related

• James Robins
• Local Average Treatment Effect
• Instrumental Variables
• Rubin Causal Model

Sources

• Robins and Greenland 1996 — Identification of Causal Effects Using Instrumental Variables Comment
• Angrist Imbens and Rubin 1996 — Identification of Causal Effects Using Instrumental Variables Rejoinder