Treatment for natural experiments: How to improve causal estimates using conceptual definitions and substantive interpretations

The local average treatment effect (LATE) estimator has enabled a wide range of empirical studies that use natural experiments to estimate causal effects from observational data. This empirical literature has overlooked a crucial assumption regarding the definition of the treatment, however—the part of the stable unit treatment value assumption referred to as the consistency assumption in epidemiology. The consequence of ignoring this assumption has been that results have been misinterpreted and over-generalized. I illustrate these problems using examples from seminal studies from the natural experiments literature and present how to improve definitions of the treatment in future studies. Correctly interpreted LATEs are substantially more specific than previously acknowledged but reclaim their internal validity. By providing clear and careful definitions of the treatment and substantive interpretations of the results, future studies will increase their usefulness by presenting the causal effect that has been actually estimated.