Analysis of Failure and Survival Data
Series Editor: Chris Chatfield, Jim Zidek, Jim Lindsey
Chapman and Hall/CRC – 2002 – 264 pages
Analysis of Failure and Survival Data is an essential textbook for graduate-level students of survival analysis and reliability and a valuable reference for practitioners. It focuses on the many techniques that appear in popular software packages, including plotting product-limit survival curves, hazard plots, and probability plots in the context of censored data. The author integrates S-Plus and Minitab output throughout the text, along with a variety of real data sets so readers can see how the theory and methods are applied. He also incorporates exercises in each chapter that provide valuable problem-solving experience.
In addition to all of this, the book also brings to light the most recent linear regression techniques. Most importantly, it includes a definitive account of the Buckley-James method for censored linear regression, found to be the best performing method when a Cox proportional hazards method is not appropriate.
Applying the theories of survival analysis and reliability requires more background and experience than students typically receive at the undergraduate level. Mastering the contents of this book will help prepare students to begin performing research in survival analysis and reliability and provide seasoned practitioners with a deeper understanding of the field.
" This book begins with a broad and basic introduction to methods for handling censored failure time data, applying these to both medical and reliability data. It then focuses intensively on the Buckley-James generalizations of the linear model for censored data. This is in contrast to most texts in this field, which focus the discussion of regression models on the theory and application of the proportional hazards (Cox) model. This book is of interest both as an easily comprehended introduction to survival analysis (with medical and reliability applications) and as an in-depth reference on the Buckley-James linear failure time model. … For a researcher with little background in failure time methods and with an interest in focusing on the extension of linear models to censored data, Analysis of Failure and Survival Data could be a useful contribution."
-Technometrics, November 2002
"…the depth and breadth of the coverage constitutes the novel and useful contribution of this text to the current collection of texts on survival analysis… Students new to the concepts of censored data analysis will find the first nine chapters informative and useful, and research specialists in survival analysis will find the last two chapters enlightening and broadening… Throughout the book, the material is presented clearly, and emphasis is placed on explaining the ideas that drive the methodology. …Also refreshing is the use of non-biomedical examples for illustrations…"
- Journal of the American Statistical Association, September 2003
"Throughout the text the author helpfully highlights definitions and important results and his style of writing is clear. …this is a good book for a reader who is new to the area. …Certainly I am pleased to have a copy on my shelves."
-A. C. Kimber, Biometrics, December 2002
Using Data to Estimate the Survival Function
Mean Time to Failure
Towards the Hazard Function
Life Expectancy at Age t
The Constant Hazard Model
The Power Hazard Model\
RELIABILITY OF SYSTEMS
Coherent Systems and Structure Functions
Paths and Cuts
Time Dependent Reliability
Empirical Survivor Function
Sample Quantile Function
CENSORING AND LIFETABLES
Type I Censoring
Type II Censoring
THE PRODUCT-LIMIT ESTIMATOR
QQ-Plots for Censored Data
PARAMETRIC SURVIVAL MODELS UNDER CENSORING
Likelihood: Type I Censoring
Likelihood: Type II Censoring
Likelihood: Random Censoring
Maximum Likelihood Procedures
The Exponential Model
The Weibull Model
PARAMETRIC REGRESSION MODELS
Basic Concepts of Proportional Hazards
Proportional Hazards for Weibull Data
Basic Concepts of Accelerated Lifetimes
Accelerated Lifetimes for Weibull Data
Diagnostics for Choosing Between Models
COX PROPORTIONAL HAZARDS
The Cox Model
Maximum Likelihood Procedures
P = 1 and the Log-Rank Test
Estimating Baseline Survival
LINEAR REGRESSION WITH CENSORED DATA
Koul-Susarla-Van Ryzin Estimators
Buckley-James Regression Methods
Properties of Buckley-James Estimators
Renovation and Least Squares
BUCKLEY-JAMES DIAGNOSTICS AND APPLICATIONS
Censored Regression Diagnostics
Applications to Heart Transplant Data
Plots of Renovated Data
Each chapter also contains exercises.