Computation, Causation, and Discovery
Clark N. Glymour, Gregory Floyd Cooper
AAAI Press, 1999 - Computers - 552 pages
In science, business, and policymaking—anywhere data are used in prediction—two sorts of problems requiring very different methods of analysis often arise. The first, problems of recognition and classification, concerns learning how to use some features of a system to accurately predict other features of that system. The second, problems of causal discovery, concerns learning how to predict those changes to some features of a system that will result if an intervention changes other features. This book is about the second—much more difficult—type of problem.
Typical problems of causal discovery are: How will a change in commission rates affect the total sales of a company? How will a reduction in cigarette smoking among older smokers affect their life expectancy? How will a change in the formula a college uses to award scholarships affect its dropout rate? These sorts of changes are interventions that directly alter some features of the system and perhaps—and this is the question—indirectly alter others.
The contributors discuss recent research and applications using Bayes nets or directed graphic representations, including representations of feedback or "recursive" systems. The book contains a thorough discussion of foundational issues, algorithms, proof techniques, and applications to economics, physics, biology, educational research, and other areas.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Causation Representation and Prediction
13 other sections not shown
adjacent analysis ancestor ancestral graph Artificial Intelligence asymptotic Bayesian network causal diagram causal discovery causal effect causal graph Causal Inference causal model causal network causal relationships causal structure collider common causes compute conditional independence connected constraint-based contains correlated errors covariance d-connects d-separation data set directed acyclic graph directed graph directed path edge entailed equivalence class estimate example exchange rates faithfulness assumption follows function given Glymour graph G graphical Heckerman Hence hidden variables inducing path latent variables lemma linear manipulated Markov condition Markov property measured variables measurement model methods Morgan Kaufmann network structure node observational data oriented output p-adjacent pair parameterization parameters PC algorithm Pearl population posterior prior probability procedures Proof random represent RSEMs sample Scheines sector selection bias Sepset(A set of variables Spirtes statistical Structural Equation Models studies subset Suppose Tetrad theorem tion treatment undirected Verma vertex vertices Xn+1 zero