Group sequential methods with applications to clinical trials. (English) Zbl 0934.62078

Jennison, Christopher; Turnbull, Bruce W.

Boca Raton, FL: Chapman & Hall/CRC. xix, 390 p. (2000).

This book is concerned with the theory of group sequential methods in the context of clinical trials, although applications to other fields are possible. The majority of the book considers two-armed parallel group designs with a single response variable and a single end point using classical inference.
There are two main themes. Firstly, different formulations of sequential testing problems are discussed based on initial experimental designs, random sample sizes and inference at termination. Secondly, the procedures are applied to data from a range of response distributions, although an example on normally distributed responses with known variance is used in most of the developments. Variations such as multiple end points, multiarmed trials, adaptive treatment assignments and Bayesian approaches are discussed in the later chapters. A final chapter gives details of the numerical computations and available computer programs for the design and evaluation of group sequential tests.

Reviewer: P.W.Jones (Keele)

MSC:

62L05	Sequential statistical design
62-02	Research exposition (monographs, survey articles) pertaining to statistics
62P10	Applications of statistics to biology and medical sciences; meta analysis
62L10	Sequential statistical analysis
62L12	Sequential estimation

Keywords:

experimental design; multiple end points; multiarmed trials; adaptive treatment assignments; Bayesian approaches

Software:

AS 195; Groupseq