An evolutionary algorithm for subset selection in causal inference models

Abstract

Researchers in all disciplines desire to identify causal relationships. Randomized experimental designs isolate the treatment effect and thus permit causal inferences. However, experiments are often prohibitive because resources may be unavailable or the research question may not lend itself to an experimental design. In these cases, a researcher is relegated to analyzing observational data. To make causal inferences from observational data, one must adjust the data so that they resemble data that might have emerged from an experiment. The data adjustment can proceed through a subset selection procedure to identify treatment and control groups that are statistically indistinguishable. Identifying optimal subsets is a challenging problem but a powerful tool. An advance in an operations research solution that is more efficient and identifies empirically more optimal solutions than other proposed algorithms is presented. The computational framework does not replace existing matching algorithms (e.g., propensity score models) but rather further enables and augments the ability of all causal inference models to identify more putatively randomized groups.