Causal Estimands for Policy Evaluation and Beyond

2025.

Sokolov B.

This paper reviews various estimands used in modern scientific and applied research to operationalize causal inquiries within the Rubin Causal Model framework. I first introduce the most widely utilized average treatment effects, such as ATE, ATT, and ATC. I then describe their popular extensions, including those targeting local and conditional treatment effects; causal interactions and mediation; effects for non-continuous outcomes, as well as for multi-valued and continuous treatments; and longitudinal treatment effects. For each of these estimands, a substantive explanation is provided, along with examples of research questions they can address. The key assumptions necessary for the identification of the most widely used effects are also discussed.

Keywords: causal inference, causal inference, evidence-based policy, treatment effects, estimands, Rubin Causa Model, estimands, evidence-based policy, Rubin Causal Model, treatment effects

Publication based on the results of: Comparative studies of culture and subjective well-being: differentiation and integration of societies in the context of global challenges (2025)