A Unified Approach to Generalized Causal Inference

Abstract

Randomized controlled trials and natural experiments have been criticized for their lack of generalizability (external validity), questioning their usefulness to social science and policy. Here I show how three common approaches to generalizability -- the heuristic, statistical, and structural approaches -- are each incomplete on their own, and how generalized causal diagrams, or g-dags, can achieve a complete representation of the problem. G-dags combine theory and evidence to (1) make inferences from a study to a population or subgroup; (2) combine two or more studies that are not generalizable on their own into a generalized inference; (3) encode and test generalizable knowledge; and (4) provide a link to boosting algorithms as generalized additive models. More generally, g-dags make explicit what is being assumed, or questioned, in discussing the generalizability of experiments, which allows for constructive discourse and informed research agendas.

Keywords: external validity, generalizability, causal diagrams, dags, experiments, field experiments, program evaluation, social experiments

JEL Classification: C9