External Validity: From Do-Calculus to Transportability Across Populations
This addresses the challenge of external validity in causal inference for researchers and scientists, providing a formal method to generalize findings across populations, though it is incremental in building on existing do-calculus frameworks.
The paper tackles the problem of transportability, or transferring causal effects from experimental studies to new populations where only observational data is available, by introducing selection diagrams and reducing transportability questions to symbolic derivations in do-calculus, enabling graph-based procedures to decide and ensure bias-free inference.
The generalizability of empirical findings to new environments, settings or populations, often called "external validity," is essential in most scientific explorations. This paper treats a particular problem of generalizability, called "transportability," defined as a license to transfer causal effects learned in experimental studies to a new population, in which only observational studies can be conducted. We introduce a formal representation called "selection diagrams" for expressing knowledge about differences and commonalities between populations of interest and, using this representation, we reduce questions of transportability to symbolic derivations in the do-calculus. This reduction yields graph-based procedures for deciding, prior to observing any data, whether causal effects in the target population can be inferred from experimental findings in the study population. When the answer is affirmative, the procedures identify what experimental and observational findings need be obtained from the two populations, and how they can be combined to ensure bias-free transport.