Counterfactuals for the Future

TL;DR

This paper explores a novel forward-looking approach to counterfactuals, emphasizing the role of exogenous noise structure in treatment decision-making, contrasting with traditional retrospective perspectives.

Contribution

It introduces the concept of forward-looking counterfactuals and analyzes their implications for treatment choice under different assumptions about exogenous noise.

Findings

Forward-looking counterfactuals can yield different treatment recommendations.

Mismatches between interventional and forward-looking approaches can cause counterintuitive results.

Exogenous noise structure significantly impacts counterfactual analysis.

Abstract

Counterfactuals are often described as 'retrospective,' focusing on hypothetical alternatives to a realized past. This description relates to an often implicit assumption about the structure and stability of exogenous variables in the system being modeled -- an assumption that is reasonable in many settings where counterfactuals are used. In this work, we consider cases where we might reasonably make a different assumption about exogenous variables, namely, that the exogenous noise terms of each unit do exhibit some unit-specific structure and/or stability. This leads us to a different use of counterfactuals -- a 'forward-looking' rather than 'retrospective' counterfactual. We introduce "counterfactual treatment choice," a type of treatment choice problem that motivates using forward-looking counterfactuals. We then explore how mismatches between interventional versus forward-looking counterfactual approaches to treatment choice, consistent with different assumptions about exogenous noise, can lead to counterintuitive results.