Competing Risks and Multistate Models with R (Use R!)

This book covers competing risks and multistate models, sometimes summarized as event history analysis. These models generalize the analysis of time to a single event (survival analysis) to analysing the timing of distinct terminal events (competing risks) and possible intermediate events (multistate models). Both R and multistate methods are promoted with a focus on nonparametric methods. Competing Risks and Multistate Models with R covers models that generalize the analysis of time to a single event (survival analysis) to analyzing the timing of distinct terminal events (competing risks) and possible intermediate events (multistate models). Both R and multistate methods are promoted with a focus on non- and semiparametric methods. This book explains hazard-based analyses of competing risks and multistate data with R. Special emphasis is placed on the interpretation of the results. A unique feature of this book is that readers are encouraged to simulate their own data based on the transition hazards only, which are the key quantities of the subsequent analyses. This simulation-based approach is supplemented with real data examples from studies in clinical medicine where the authors have been involved. This book is aimed at data analysts, with a background in standard survival analysis, who wish to understand, analyse and interpret more complex event histories with R. It is also suitable for graduate courses in biostatistics, statistics and epidemiological methods. The real data examples, R packages, and the entire R code used in the book are available online. The authors are affiliated with the Institute of Medical Biometry and Medical Informatics, University Medical Center Freiburg and the Freiburg Center for Data Analysis and Modelling, University of Freiburg, Germany. Jan Beyersmann is Senior Statistician and serves on the editorial board of Statistics in Medicine. Arthur Allignol is Statistician and has contributed several R packages on competing risks and multistate models. Martin Schumacher is Professor of Biostatistics and Director of the Institute of Medical Biometry and Medical Informatics, Freiburg. He has been involved in theoretical developments as well as in practical applications of survival analyses and their extensions over many years. --2e de couv Front Matter....Pages i-xi Front Matter....Pages 1-1 Data examples....Pages 3-7 An informal introduction to hazard-based analyses....Pages 9-38 Front Matter....Pages 39-39 Multistate modelling of competing risks....Pages 41-53 Nonparametric estimation....Pages 55-88 Proportional hazards models....Pages 89-153 Nonparametric hypothesis testing....Pages 155-158 Further topics in competing risks....Pages 159-166 Front Matter....Pages 167-167 Multistate models and their connection to competing risks....Pages 169-175 Nonparametric estimation....Pages 177-195 Proportional transition hazards models....Pages 197-209 Time-dependent covariates and multistate models....Pages 211-226 Further topics in multistate modelling....Pages 227-230 Back Matter....Pages 231-245