Recursive Partitioning in the Health Sciences

Front Cover
Springer Science & Business Media, Mar 30, 1999 - Science - 226 pages
0 Reviews
Multiple complex pathways, characterized by interrelated events and con ditions, represent routes to many illnesses, diseases, and ultimately death. Although there are substantial data and plausibility arguments supporting many conditions as contributory components of pathways to illness and disease end points, we have, historically, lacked an effective methodology for identifying the structure of the full pathways. Regression methods, with strong linearity assumptions and data-based constraints on the extent and order of interaction terms, have traditionally been the strategies of choice for relating outcomes to potentially complex explanatory pathways. How ever, nonlinear relationships among candidate explanatory variables are a generic feature that must be dealt with in any characterization of how health outcomes come about. Thus, the purpose of this book is to demon strate the effectiveness of a relatively recently developed methodology recursive partitioning-as a response to this challenge. We also compare and contrast what is learned via recursive partitioning with results ob tained on the same data sets using more traditional methods. This serves to highlight exactly where--and for what kinds of questions-recursive partitioning-based strategies have a decisive advantage over classical re gression techniques. This book is suitable for three broad groups of readers: (1) biomedical re searchers, clinicians, public health practitioners including epidemiologists, health service researchers, environmental policy advisers; (2) consulting statisticians who can use the recursive partitioning technique as a guide in providing effective and insightful solutions to clients' problems; and (3) statisticians interested in methodological and theoretical issues.
 

What people are saying - Write a review

We haven't found any reviews in the usual places.

Contents

Introduction
1
11 Examples Using CART
2
12 The Statistical Problem
4
13 Outline of the Methodology
5
A Practical Guide to Tree Construction
7
21 The Elements of Tree Construction
9
22 Splitting a Node
10
23 Terminal Nodes
15
83 Implementation
100
84 Survival Trees for the Western Collaborative Group Study Data
101
Regression Trees and Adaptive Splines for a Continuous Response
105
91 Tree Representation of Spline Model and Analysis of Birth Weight
106
92 Regression Trees
108
93 The Profile of MARS Models
112
94 Modified MARS Forward Procedure
115
95 MARS BackwardDeletion Step
118

24 Download and Use of Software
16
Logistic Regression
21
32 A Logistic Regression Analysis
22
Classification Trees for a Binary Response
29
42 Determination of Terminal Nodes
32
43 The Standard Error of R
40
44 TreeBased Analysis of the Yale Pregnancy Outcome Study
41
45 An Alternative Pruning Approach
43
46 Localized CrossValidation
47
47 Comparison Between TreeBased and Logistic Regression Analyses
49
48 Missing Data
53
49 Tree Stability
55
410 Implementation
56
RiskFactor Analysis Using TreeBased Stratification
61
52 The Analysis
63
Analysis of Censored Data Examples
71
62 TreeBased Analysis for the Western Collaborative Group Study Data
74
Analysis of Censored Data Concepts and Classical Methods
79
72 Parametric Regression for Censored Data
87
Analysis of Censored Data Survival Trees
93
82 Pruning a Survival Tree
99
96 The Best Knot
120
97 Restrictions on the Knot
123
98 Smoothing Adaptive Splines
127
99 Numerical Examples
129
Analysis of Longitudinal Data
137
102 The Notation and a General Model
139
103 MixedEffects Models
140
104 Semiparametric Models
143
105 Adaptive Spline Models
144
106 Regression Trees for Longitudinal Data
167
Analysis of Multiple Discrete Responses
173
111 Parametric Methods for Binary Responses
175
112 Classification Trees for Multiple Binary Responses
183
Analysis of BROCS Data
187
114 Polytomous and Longitudinal Responses
195
Appendix
201
122 The Script for Running RTREE Manually
205
123 The inf File
209
References
213
Index
225
Copyright

Other editions - View all

Common terms and phrases

Popular passages

Page 217 - Giovannucci, A. Ascherio, EB Rimm, MJ Stampfer, GA Colditz and WC Willett, Intake of carotenoids and retinol in relation to risk of prostate cancer. J. Natl.
Page 221 - G. Poggi and RA Olshen. Pruned tree-structured vector quantization of medical images with segmentation and improved prediction.
Page iv - Department of Epidemiology and Public Health, School of Medicine, Yale University, 60 College Street, PO Box 3333, New Haven, CT 06510, USA.
Page 217 - A Recursive Partitioning Decision Rule for Nonparametric Classification," IEEE Trans, on Computers, Vol C-26, pp.
Page 217 - L. GORDON AND RA OLSHEN, Asymptotically efficient solutions to the classification problem, Annals of Statistics, 6, (1978), 515-533.

References to this book

All Book Search results »

About the author (1999)

Zhang, Yale University, New Haven, CT.

Bibliographic information