Causal Models and Intelligent Data Management

by Gammerman, Alex

• ISBN13: 9783540663287
• ISBN10: 3540663282
• Format: Hardcover
• Copyright: 1999-10-01
• Publisher: Springer-Verlag New York Inc

Summary

Data analysis and inference have traditionally been research areas of statistics. However, the need to electronically store, manipulate and analyze large-scale, high-dimensional data sets requires new methods and tools, new types of databases, new efficient algorithms, new data structures, etc. - in effect new computational methods.This monograph presents new intelligent data management methods and tools, such as the support vector machine, and new results from the field of inference, in particular of causal modeling. In 11 well-structured chapters, leading experts map out the major tendencies and future directions of intelligent data analysis. The book will become a valuable source of reference for researchers exploring the interdisciplinary area between statistics and computer science as well as for professionals applying advanced data analysis methods in industry and commerce. Students and lecturers will find the book useful as an introduction to the area.

Table of Contents

Part I. Causal Models
Statistics, Causality, and Graphs	3	(14)
J. Pearl
A Century of Denial	3	(2)
Researchers in Search of a Language	5	(3)
Graphs as a Mathematical Language	8	(5)
The Challenge	13	(4)
References	14	(3)
Causal Conjecture	17	(16)
Glenn Shafer
Introduction	17	(1)
Variables in a Probability Tree	18	(1)
Causal Uncorrelatedness	19	(1)
Three Positive Causal Relations	20	(2)
Linear Sign	22	(4)
Causal Uncorrelatedness Again	26	(1)
Scored Sign	27	(1)
Tracking	28	(5)
References	32	(1)
Who Needs Counterfactuals	33	(18)
A. P. Dawid
Introduction	33	(2)
Decision-Theoretic Framework	33	(1)
Unresponsiveness and Insensitivity	34	(1)
Counterfactuals	35	(1)
Problems of Causal Inference	36	(1)
Causes of Effects	36	(1)
Effects of Causes	36	(1)
The Counterfactual Approach	37	(2)
The Counterfactual Setting	37	(1)
Counterfactual Assumptions	38	(1)
Homogeneous Population	39	(4)
Experiment and Inference	40	(3)
Decision-Analytic Approach	43	(2)
Sheep and Goats	45	(2)
ACE	45	(1)
Neyman and Fisher	45	(1)
Bioequivalence	46	(1)
Causes of Effects	47	(1)
A Different Approach	48	(1)
Conclusion	48	(3)
References	49	(2)
Causality: Independence and Determinism	51	(16)
Nancy Cartwright
Introduction	51	(10)
Conclusion	61	(6)
References	63	(4)
Part II. Intelligent Data Management
Intelligent Data Analysis and Deep Understanding	67	(14)
David J. Hand
Introduction	67	(1)
The Question: The Strategy	68	(6)
Diminishing Returns	74	(4)
Conclusion	78	(3)
References	79	(2)
Learning Algorithms in High Dimensional Spaces	81	(8)
A. Gammerman
V. Vovk
Introduction	81	(1)
SVM for Pattern Recognition	82	(2)
Dual Representation of Pattern Recognition	83	(1)
SVM for Regression Estimation	84	(2)
Dual Representation of Regression Estimation	84	(1)
SVM Applet and Software	85	(1)
Ridge Regression and Least Squares Methods in Dual Variables	86	(1)
Transduction	87	(1)
Conclusion	88	(1)
References	88	(1)
Learning Linear Causal Models by MML Sampling	89	(23)
Chris S. Wallace
Kevin B. Korb
Introduction	89	(1)
Minimum Message Length Principle	90	(2)
The Model Space	92	(1)
The Message Format	93	(2)
Equivalence Sets	95	(3)
Small Effects	96	(1)
Partial Order Equivalence	97	(1)
Structural Equivalence	97	(1)
Explanation Length	98	(1)
Finding Good Models	98	(4)
Sampling Control	102	(1)
By-products	102	(1)
Prior Constraints	102	(1)
Test Results	103	(3)
Remarks on Equivalence	106	(4)
Small Effect Equivalence	106	(1)
Equivalence and Causality	107	(3)
Conclusion	110	(2)
References	110	(2)
Game Theory Approach to Multicommodity Flow Network Vulnerability Analysis	112	(8)
Y. E. Malashenko
N. M. Novikova
O. A. Vorobeichikova
References	118	(2)
On the Accuracy of Stochastic Complexity Approximations	120	(17)
Petri Kontkanen
Petri Myllymaki
Tomi Silander
Henry Tirri
Introduction	120	(2)
Stochastic Complexity and Its Applications	122	(2)
Approximating the Stochastic Complexity in the Incomplete Data Case	124	(1)
Empirical Results	125	(7)
The Problem	125	(2)
The Experimental Setting	127	(2)
The Algorithms	129	(1)
Results	130	(2)
Conclusion	132	(5)
References	134	(3)
AI Modelling for Data Quality Control	137	(14)
Xiaohui Liu
Introduction	137	(1)
Statistical Approaches to Outliers	137	(2)
Outlier Detection and Analysis	139	(1)
Visual Field Test	139	(2)
Outlier Detection	141	(2)
Self-Organising Maps (SOM)	141	(1)
Applications of SOM	142	(1)
Outlier Analysis by Modelling `Real Measurements'	143	(2)
Outlier Analysis by Modelling Noisy Data	145	(2)
Noise Model I: Noise Definition	145	(1)
Noise Model II: Construction	146	(1)
Noise Elimination	147	(1)
Concluding Remarks	147	(4)
References	148	(3)
New Directions in Text Categorization	151	(30)
Richard S. Forsyth
Introduction	151	(2)
Machine Learning for Text Classification	153	(3)
Radial Basis Functions and the Bard	156	(2)
An Evolutionary Algorithm for Text Classification	158	(3)
Text Classification by Vocabulary Richness	161	(2)
Text Classification with Frequent Function Words	163	(1)
Do Authors Have Semantic Signatures	164	(2)
Syntax with Style	166	(1)
Intermezzo	167	(1)
Some Methods of Textual Feature-Finding	168	(9)
Progressive Pairwise Chunking	169	(1)
Monte Carlo Feature Finding	170	(3)
How Long Is a Piece of Substring	173	(2)
Comparative Testing	175	(2)
Which Methods Work Best?---A Benchmarking Study	177	(3)
Discussion	180	(1)
In Praise of Semi-Crude Bayesianism	180	(1)
What's So Special About Linguistic Data	180	(1)
References	181