Causation, Prediction, and SearchThis book is intended for anyone, regardless of discipline, who is interested in the use of statistical methods to help obtain scientific explanations or to predict the outcomes of actions, experiments or policies. Much of G. Udny Yule's work illustrates a vision of statistics whose goal is to investigate when and how causal influences may be reliably inferred, and their comparative strengths estimated, from statistical samples. Yule's enterprise has been largely replaced by Ronald Fisher's conception, in which there is a fundamental cleavage between experimental and non experimental inquiry, and statistics is largely unable to aid in causal inference without randomized experimental trials. Every now and then members of the statistical community express misgivings about this turn of events, and, in our view, rightly so. Our work represents a return to something like Yule's conception of the enterprise of theoretical statistics and its potential practical benefits. If intellectual history in the 20th century had gone otherwise, there might have been a discipline to which our work belongs. As it happens, there is not. We develop material that belongs to statistics, to computer science, and to philosophy; the combination may not be entirely satisfactory for specialists in any of these subjects. We hope it is nonetheless satisfactory for its purpose. |
Contents
Formal Preliminaries | 25 |
Axioms and Explications | 41 |
Statistical Indistinguishability | 87 |
Discovery Algorithms for Causally Sufficient Structures | 103 |
Discovery Algorithms without Causal Sufficiency | 163 |
Prediction | 201 |
Regression Causation and Prediction | 238 |
The Design of Empirical Studies | 259 |
Other editions - View all
Causation, Prediction, and Search Peter Spirtes,Clark N. Glymour,Richard Scheines Limited preview - 2000 |
Causation, Prediction, and Search Peter Spirtes,Clark Glymour,Richard Scheines No preview available - 1993 |
Common terms and phrases
assumption causal graph causal inference Causal Markov Condition causal structure causally sufficient choke point collider conditional distribution conditional independence relations conditional probability contains covariance d-connects D-path d-separated given descendant determine deterministic Deterministic(V direct manipulation directed acyclic graph directed edge directed graph directed path endpoints equation estimate example experimental figure follows GComb graph G Gunman Hence hypothesis I-map implied by G independent conditional inducing path graph latent variables lemma linear coefficients linearly implied LISREL lung cancer Markov Condition measured variables non-collider oriented inducing path output pair parameters parent partially oriented inducing PC algorithm PIJPKL PILPJK population prediction probability distribution Proof random variables regression regressors reliable sample satisfies the Markov set of variables Simpson's paradox Smoking subgraph subpath subset Suppose tests Theorem treatment trek undirected unmanipulated unmeasured common causes values vanishing partial correlations vanishing tetrad differences vertex vertex set zero