This paper introduces causal scoring as a novel approach to frame causal estimation in the context of decision making. Causal scoring entails the estimation of scores that support decision making by providing insights into causal effects. We present three valuable causal interpretations of these scores: effect estimation (EE), effect ordering (EO), and effect classification (EC). In the EE interpretation, the causal score represents the effect itself. The EO interpretation implies that the score can serve as a proxy for the magnitude of the effect, enabling the sorting of individuals based on their causal effects. The EC interpretation enables the classification of individuals into high- and low-effect categories using a predefined threshold. We demonstrate the value of these alternative causal interpretations (EO and EC) through two key results. First, we show that aligning the statistical modeling with the desired causal interpretation improves the accuracy of causal estimation. Second, we establish that more flexible causal interpretations are plausible in a wider range of settings and propose conditions to assess their validity. We showcase the practical utility of causal scoring through diverse scenarios, including situations involving unobserved confounding due to self-selection, lack of data on the primary outcome of interest, or lack of data on how individuals behave when intervened. These examples illustrate how causal scoring facilitates reasoning about flexible causal interpretations of statistical estimates in various contexts. They encompass confounded estimates, effect estimates on surrogate outcomes, and even predictions about non-causal quantities as potential causal scores.
翻译:暂无翻译