Causal Mechanism-based Model Construction

We propose a framework for building graph­ ical causal model that is based on the con­ cept of causal mechanisms. Causal models are intuitive for human users and, more im­ portantly, support the prediction of the ef­ fect of manipulation. We describe an imple­ mentation of the proposed framework as an interactive model construction module, Ima­ GeNie, in SMILE (Structural Modeling, In­ ference, and Learning Engine) and in GeNie (SMILE's Windows user interface).