Rubin Causal Model

Abstract

The Rubin Causal Model (RCM), a framework for causal inference, has three distinctive features. First, it uses ‘potential outcomes’ to define causal effects at the unit level, first introduced by Neyman in the context of randomized experiments and randomization-based inference, but not used formally in non-randomized studies or with other modes of inference until Rubin (1974; 1975). Second is its formal use of a probabilistic assignment mechanism, which mathematically describes how treatments are given to units, with possible dependence on background variables and the potential outcomes themselves. Third is an optional probability distribution on all variables, including the potential outcomes, which thereby unifies frequentist and model-based forms of statistical inference for causal effects within one framework