|
Abstract:
|
Researchers often need to determine whether a specific exposure, or something else, caused an individual's outcome. To answer questions of causality in which the exposure and outcome have already been observed, researchers have suggested estimating the probability of causation (PC). PC is especially important in court, for example in class action lawsuits, and in public policy, for example in determining who would benefit most from a program. However, the current estimation methods for PC make strong parametric assumptions, or are inefficient and do not easily yield inferential tools. We derive an influence-function-based nonparametric estimator for PC, which allows for simple interpretation and valid inference by making only weak structural assumptions. We compare our proposed estimator to the current plug-in methods, both parametric and nonparametric, by simulation. Finally, we present an application of our estimation method by using data from a randomized controlled trial from Western Kenya.
|
