Content area
Full Text
This book seeks to integrate research on cause and effect inference from cognitive science, econometrics, epidemiology, philosophy, and statistics. It puts forward the work of its author, his collaborators, and others over the past two decades as a new account of cause and effect inference that can aid practical researchers in many fields, including econometrics. Pearl adheres to several propositions on cause and effect inference. Though cause and effect relations are fundamentally deterministic (he explicitly excludes quantum mechanical phenomena from his concept of cause and effect), cause and effect analysis involves probability language. Probability language helps to convey uncertainty about cause and effect relations but is insufficient to fully express those relations. In addition to conditional probabilities of events, cause and effect analysis requires graphs or diagrams and a language that distinguishes intervention or manipulation from observation. Cause and effect analysis also requires counterfactual reasoning and causal assumptions in addition to observations and statistical assumptions.
Chapter 1 sketches some of the ingredients of the new approach to cause and effect inference: probability theory, graphs, Bayesian causal networks, causal models, and causal and statistical terminology. Chapter 2 builds the elements of Chapter 1 into a theory of inferred causation. Chapter 3 focuses on causal diagrams and identifying causal effects. Chapter 4 studies intervention or manipulation and direct causal effects. Chapter 5 considers causality and structural equation models. Chapter 6 examines Simpson's paradox and confounding. Chapter 7 blends structural modeling with counterfactual reasoning. Chapter 8 is an approach to imperfect random assignment experiments through bounding effects and counterfactuals. Chapter 9 analyzes notions of necessary cause and sufficient cause. Chapter 10 explicates a concept of single event causality. The epilogue is a public lecture that Pearl gave at UCLA that, in mostly not too technical language, places the new approach to causality within the long history of thought on the subject.
The interdisciplinary nature of the book, a great strength, at times makes it difficult to read because its theory of inferred causation blends the languages of econometrics and statistics, mathematical graph theory, and Bayesian networks with philosophical notions of cause and effect. However, Pearl facilitates reader understanding by using reasonably straightforward mathematics and examples to help to connect the separate disciplinary discourses. Nevertheless, an only semiformal approach...