Causality by Judea Pearl

Models, Reasoning, and Inference

Introduces a formal framework for reasoning about cause and effect using graphical models, structural equations, and the do-operator, explaining how to distinguish correlation from causation, identify confounding, and compute the effects of interventions. It presents criteria for identifiability, tools for mediation analysis and policy evaluation, and a logic of counterfactuals, all unified by causal diagrams and do-calculus, with examples spanning social sciences, medicine, and AI.

Purchase from Bookshop.org