Hosmer / Lemeshow / May Applied Survival Analysis

Regression Modeling of Time to Event Data
2. Auflage 2011
ISBN: 978-0-470-25800-2
Verlag: John Wiley & Sons
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 416 Seiten, E-Book

Reihe: Wiley Series in Probability and Statistics

THE MOST PRACTICAL, UP-TO-DATE GUIDE TO MODELLING AND ANALYZINGTIME-TO-EVENT DATA--NOW IN A VALUABLE NEW EDITION
Since publication of the first edition nearly a decade ago,analyses using time-to-event methods have increase considerably inall areas of scientific inquiry mainly as a result ofmodel-building methods available in modern statistical softwarepackages. However, there has been minimal coverage in the availableliterature to9 guide researchers, practitioners, and students whowish to apply these methods to health-related areas of study.Applied Survival Analysis, Second Edition provides a comprehensiveand up-to-date introduction to regression modeling fortime-to-event data in medical, epidemiological, biostatistical, andother health-related research.
This book places a unique emphasis on the practical andcontemporary applications of regression modeling rather than themathematical theory. It offers a clear and accessible presentationof modern modeling techniques supplemented with real-world examplesand case studies. Key topics covered include: variable selection,identification of the scale of continuous covariates, the role ofinteractions in the model, assessment of fit and model assumptions,regression diagnostics, recurrent event models, frailty models,additive models, competing risk models, and missing data.
Features of the Second Edition include:
* Expanded coverage of interactions and the covariate-adjustedsurvival functions
* The use of the Worchester Heart Attack Study as the mainmodeling data set for illustrating discussed concepts andtechniques
* New discussion of variable selection with multivariablefractional polynomials
* Further exploration of time-varying covariates, complex withexamples
* Additional treatment of the exponential, Weibull, andlog-logistic parametric regression models
* Increased emphasis on interpreting and using results as well asutilizing multiple imputation methods to analyze data with missingvalues
* New examples and exercises at the end of each chapter
Analyses throughout the text are performed using Stata®Version 9, and an accompanying FTP site contains the data sets usedin the book. Applied Survival Analysis, Second Edition is an idealbook for graduate-level courses in biostatistics, statistics, andepidemiologic methods. It also serves as a valuable reference forpractitioners and researchers in any health-related field or forprofessionals in insurance and government.

Autoren/Hrsg.

Hosmer, David W.

Lemeshow, Stanley

May, Susanne

Inhaltsverzeichnis

Preface.
1. Introduction to Regression Modeling of SurvivalData.
1.1 Introduction.
1.2 Typical Censoring Mechanisms.
1.3 Example Data Sets.
Exercises.
2. Descriptive Methods for Survival Data.
2.1 Introduction.
2.2 Estimating the Survival Function.
2.3 Using the Estimated Survival Function.
2.4 Comparison of Survival Functions.
2.5 Other Functions of Survival Time and Their Estimators.
Exercises.
3. Regression Models for Survival Data.
3.1 Introduction.
3.2 Semi-Parametric Regression Models.
3.3 Fitting the Proportional Hazards Regression Model.
3.4 Fitting the Proportional Hazards Model with Tied SurvivalTimes.
3.5 Estimating the Survival Function of the Proportional HazardsRegression Model.
Exercises.
4. Interpretation of a Fitted Proportional Hazards RegressionModel.
4.1 Introduction.
4.2 Nominal Scale Covariate.
4.3 Continuous Scale Covariate.
4.4 Multiple-Covariate Models.
4.5 Interpreting and Using the Estimated Covariate-AdjustedSurvival Function.
Exercises.
5. Model Development.
5.1 Introduction.
5.2 Purposeful Selection of Covariates.
5.2.1 Methods to examine the scale of continuous covariates inthe log hazard.
5.2.2 An example of purposeful selection of covariates.
5.3 Stepwise, Best-Subsets and Multivariable FractionalPolynomial Methods of Selecting Covariates.
5.3.1 Stepwise selection of covariates.
5.3.2 Best subsets selection of covariates.
5.3.3 Selecting covariates and checking their scale usingmultivariable fractional polynomials.
5.4 Numerical Problems.
Exercises.
6. Assessment of Model Adequacy.
6.1 Introduction.
6.2 Residuals.
6.3 Assessing the Proportional Hazards Assumption.
6.4 Identification of Influential and Poorly Fit Subjects.
6.5 Assessing Overall Goodness-of-Fit.
6.6 Interpreting and Presenting Results From the FinalModel.
Exercises.
7. Extensions of the Proportional Hazards Model.
7.1 Introduction.
7.2 The Stratified Proportional Hazards Model.
7.3 Time-Varying Covariates.
7.4 Truncated, Left Censored and Interval Censored Data.
Exercises.
8. Parametric Regression Models.
8.1 Introduction.
8.2 The Exponential Regression Model.
8.3 The Weibull Regression Model.
8.4 The Log-Logistic Regression Model.
8.5 Other Parametric Regression Models.
Exercises.
9. Other Models and Topics.
9.1 Introduction.
9.2 Recurrent Event Models.
9.3 Frailty Models.
9.4 Nested Case-Control Studies.
9.5 Additive Models.
9.6 Competing Risk Models.
9.7 Sample Size and Power.
9.8 Missing Data.
Exercises.
Appendix 1: The Delta Method.
Appendix 2: An Introduction to the Counting Process Approach toSurvival Analysis.
Appendix 3: Percentiles for Computation of the Hall and WellnerConfidence Band.
References.
Index.

Über Autor(innen)

David W. Hosmer, PhD, is Professor Emeritus of Biostatisticsin the School of Public Health and Heatlth Sciences at theUniversity of Massachusetts Amherst. Dr. Hosmer is the coauthor ofApplied Logistic Regression, published by Wiley.
Stanley Lemeshow, PhD, is Professor and Dean of theCollege of Public Health at The Ohio State University. Dr. Lemeshowhas over thirty-five years of academic experience in the areas ofregression, categorical data methods, and sampling methods. He isthe coauthor of Sampling of Population: Methods andApplication and Applied Logistic Regression, bothpublished by Wiley.
Susanne May, PhD, is Assistant Professor of Biostatisticsat the University of California, San Diego. Dr. May has over twelveyears of experience in providing statistical support forhealth-related research projects.