Survival analysis. Techniques for censored and truncated data. (English) Zbl 0871.62091

Statistics for Biology and Health. New York, NY: Springer. xiv, 502 p. (1997).
This is yet another book on survival analysis for beginners. As for most of the predecessors, it is focused on applications in medicine and biology. The authors’ aim is to make the complex counting process theory accessible to applied researchers lacking an advanced mathematical background. They also claim that the book is suitable as a text book for a graduate level course in survival analysis, where the minimum prerequisite is a traditional course in statistical methodology.
The book is divided into five major themes. The first theme introduces basic concepts and terminology. The second theme is the estimation of summary statistics based on censored and truncated data. This includes not only usual things like the survival and the cumulative hazard functions, but also measures of centrality, such as the median and the mean. The third theme is hypothesis testing, including the log-rank test and the generalized Wilcoxon test. The fourth theme is regression analysis, with special emphasis on the proportional hazards model. The final theme is multivariate models for survival data. Each section of the book ends with a set of practical notes relevant for that section. Technical details and advanced topics, which can be skipped without loss of continuity, are also gathered at the end of each section. The book ends with four appendices containing numerical techniques for maximization, large sample tests based on likelihood theory, statistical tables, and selected data sets.


62P10 Applications of statistics to biology and medical sciences; meta analysis
62-01 Introductory exposition (textbooks, tutorial papers, etc.) pertaining to statistics
62M99 Inference from stochastic processes