E-Book Overview
In recent years, small groups of statisticians, computer scientists, and philosophers have developed an account of how partial causal knowledge can be used to compute the effect of actions and how causal relations can be learned, at least by computers. The representations used in the emerging theory are causal Bayes nets or graphical causal models. In his new book, Clark Glymour provides an informal introduction to the basic assumptions, algorithms, and techniques of causal Bayes nets and graphical causal models in the context of psychological examples. He demonstrates their potential as a powerful tool for guiding experimental inquiry and for interpreting results in developmental psychology, cognitive neuropsychology, psychometrics, social psychology, and studies of adult judgment. Using Bayes net techniques, Glymour suggests novel experiments to distinguish among theories of human causal learning and reanalyzes various experimental results that have been interpreted or misinterpreted--without the benefit of Bayes nets and graphical causal models. The capstone illustration is an analysis of the methods used in Herrnstein and Murray’s book The Bell Curve ; Glymour argues that new, more reliable methods of data analysis, based on Bayes nets representations, would lead to very different conclusions from those advocated by Herrnstein and Murray.
E-Book Content
The Mind’s Arrows
The Mind’s Arrows Bayes Nets and Graphical Causal Models in Psychology
Clark Glymour
A Bradford Book The MIT Press Cambridge, Massachusetts London, England
( 2001 Massachusetts Institute of Technology All rights reserved. No part of this book may be reproduced in any form by any electronic or mechanical means (including photocopying, recording, and information storage and retrieval) without permission in writing from the publisher. This book was set in Sabon by Asco Typesetters, Hong Kong, on 3B2 and was printed and bound in the United States of America. First printing, 2001 Library of Congress Cataloging-in-Publication Data Glymour, Clark N. The mind’s arrows : Bayes nets and graphical causal models in psychology / Clark Glymour. p. cm. ‘‘A Bradford book.’’ Includes bibliographical references and index. ISBN 0-262-07220-3 (alk. paper) 1. Psychology—Methodology. 2. Prediction theory. 3. Causation. I. Title. BF38.5 .G59 2001 150 0 .1—dc21 2001032623
In memory of my teachers Cynthia Ann Schuster and Wesley Charles Salmon
Contents
Acknowledgments
xi
1
Introduction
I
Developmental Psychology and Discovery
2
Android Epistemology for Babies 7 2.1 Introduction 7 2.2 Children 8 2.3 The Platonic Theory of Cognitive Development 2.4 The Theory Theory 13 2.5 Android Epistemology 14 2.6 Issues 16
3
1
10
Another Way for Nerds to Make Babies: The Frame Problem and Causal Inference in Developmental Psychology 19 3.1 The Frame Problem 19 3.2 A Toy Introduction to the Markov Assumption 21 3.3 The Causal Markov Assumption 24 3.4 Causal Bayes Nets 27 3.5 The Utility of Causal Bayes Nets 29 3.6 Heuristics and Concept Formation 34 3.7 Experiments 42 3.8 Conclusion 45
II Adult Judgements of Causation 4
5
A Puzzling Experiment 51 4.1 The Baker Experiment 51 4.2 Of Mice and Men 55
49
viii
Contents
5
The Puzzle Resolved
63
6
Marilyn vos Savant Meets Rescorla and Wagner 69 6.1 Introduction 69 6.2 Conditional Dependence and the Monte Hall Game 6.3 Testing Rescorla and Wagner’s Model 71
69
7
Cheng Models 75 7.1 Introduction 75 7.2 Cheng’s Model of Human Judgement of Generative Causal Power 76 7.3 Preventive Causes 79 7.4 Generative Interaction 79 7.5 Cheng Models as Bayes Nets 82 7.6 Discovering the Causal