Interactive and Dynamic Graphics for Data Analysis

by Cook, Dianne; Swayne, Deborah F.; Buja, Andreas (CON); Lang, Duncan Temple (CON); Hofmann, Heike (CON); Wickham, Hadley (CON)

• ISBN13: 9780387717616
• ISBN10: 0387717617
• Format: Paperback
• Copyright: 2007-10-26
• Publisher: Springer Verlag

Summary

This richly illustrated book describes the use of interactive and dynamic graphics as part of multidimensional data analysis. Chapters include clustering, supervised classification, and working with missing values. A variety of plots and interaction methods are used in each analysis, often starting with brushing linked low-dimensional views and working up to manual manipulation of tours of several variables. The role of graphical methods is shown at each step of the analysis, not only in the early exploratory phase, but in the later stages, too, when comparing and evaluating models. All examples are based on freely available software: GGobi for interactive graphics and R for static graphics, modeling, and programming. The printed book is augmented by a wealth of material on the web, encouraging readers follow the examples themselves. The web site has all the data and code necessary to reproduce the analyses in the book, along with movies demonstrating the examples. The book may be used as a text in a class on statistical graphics or exploratory data analysis, for example, or as a guide for the independent learner. Each chapter ends with a set of exercises. The authors are both Fellows of the American Statistical Association, past chairs of the Section on Statistical Graphics, and co-authors of the GGobi software. Dianne Cook is Professor of Statistics at Iowa State University. Deborah Swayne is a member of the Statistics Research Department at AT&T Labs.

Author Biography

Dianne Cook is Professor of Statistics at Iowa State University.

Table of Contents

Preface	p. V
Technical Notes	p. XIII
List of Figures	p. XV
Introduction	p. 1
Data visualization: beyond the third dimension	p. 1
Statistical data visualization: goals and history	p. 3
Getting down to data	p. 4
Getting real: process and caveats	p. 8
Interactive investigation	p. 15
The Toolbox	p. 17
Introduction	p. 17
Plot types	p. 19
Univariate plots	p. 19
Bivariate plots	p. 21
Multivariate plots	p. 24
Plot arrangement	p. 34
Plot manipulation and enhancement	p. 35
Brushing	p. 35
Identification	p. 41
Scaling	p. 41
Subset selection	p. 42
Line segments	p. 43
Interactive drawing	p. 43
Dragging points	p. 43
Tools available elsewhere	p. 44
Recap	p. 45
Exercises	p. 45
Missing Values	p. 47
Background	p. 48
Exploring missingness	p. 49
Shadow matrix	p. 49
Getting started: missings in the "margins"	p. 52
A limitation	p. 53
Tracking missings using the shadow matrix	p. 55
Imputation	p. 55
Mean values	p. 56
Random values	p. 56
Multiple imputation	p. 58
Recap	p. 61
Exercises	p. 62
Supervised Classification	p. 63
Background	p. 64
Classical multivariate statistics	p. 65
Data mining	p. 66
Studying the fit	p. 69
Purely graphics: getting a picture of the class structure	p. 70
Overview of Italian Olive Oils	p. 70
Building classifiers to predict region	p. 71
Separating the oils by area within each region	p. 73
Taking stock	p. 77
Numerical methods	p. 77
Linear discriminant analysis	p. 77
Trees	p. 81
Random forests	p. 83
Neural networks	p. 88
Support vector machine	p. 92
Examining boundaries	p. 97
Recap	p. 99
Exercises	p. 99
Cluster Analysis	p. 103
Background	p. 105
Purely graphics	p. 107
Numerical methods	p. 111
Hierarchical algorithms	p. 111
Model-based clustering	p. 113
Self-organizing maps	p. 119
Comparing methods	p. 122
Characterizing clusters	p. 125
Recap	p. 126
Exercises	p. 127
Miscellaneous Topics	p. 129
Inference	p. 129
Longitudinal data	p. 134
Network data	p. 139
Multidimensional scaling	p. 145
Exercises	p. 151
Datasets	p. 153
Tips	p. 153
Australian Crabs	p. 154
Italian Olive Oils	p. 155
Flea Beetles	p. 157
PRIM7	p. 157
Tropical Atmosphere-Ocean Array (TAO)	p. 159
Primary Biliary Cirrhosis (PBC)	p. 161
Spam	p. 162
Wages	p. 164
Rat Gene Expression	p. 166
Arabidopsis Gene Expression	p. 168
Music	p. 171
Cluster Challenge	p. 172
Adjacent Transposition Graph	p. 172
Florentine Families	p. 173
Morse Code Confusion Rates	p. 174
Personal Social Network	p. 175
References	p. 177
Index	p. 185
Table of Contents provided by Ingram. All Rights Reserved.