Flowgraph models for multistate time-to-event data. (English) Zbl 1055.62123

Huzurbazar, Aparna V.

Wiley Series in Probability and Statistics. Hoboken, NJ: John Wiley & Sons (ISBN 0-471-26514-4/hbk; 978-0-471-68656-9/ebook). xii, 270 p. (2005).

This book is intended as a text for graduate students and as a reference for workers in biostatistics, systems engineering and other domains using stochastic processes. The prerequisite is a honest one-year graduate course in probability and statistics. The introductory part of some chapters (5, 7 and 9) may serve as a text for a graduate course in stochastic processes. Numerous illustrations, examples and exercises are included for better understanding. It represents an open window to applications of this methodology to diverse real world problems from medicine to engineering.
This book introduces flowgraph models for time-to-event data. The flowgraph models are multistate models for time-to-event data that provide an alternative and innovative approach for the analysis of such data. They model semi-Markov processes and allow for a variety of distributions. They also easily handle reversibility. The most important feature of this book is that the flowgraph models for time-to-event data are illustrated by systematic applications. Fruitful medical and engineering examples and applications are presented (e.g., AIDS, diabetic retinopathy, cellular telephone network) along with computer code as needed. The appendix is devoted to moment generating functions.

Reviewer: Florin Gorunescu (Craiova)

MSC:

62P10	Applications of statistics to biology and medical sciences; meta analysis
62M99	Inference from stochastic processes
62-02	Research exposition (monographs, survey articles) pertaining to statistics
62P30	Applications of statistics in engineering and industry; control charts
90C40	Markov and semi-Markov decision processes
62-09	Graphical methods in statistics (MSC2010)

Keywords:

flowgraph models; moment generating function; survivor and reliability functions; bayesian prediction; saddlepoint approximation; semi-Markov processes; queuing systems; computer code