The optimal design of blocked and split-plot experiments. (English) Zbl 1008.62068

Goos, Peter

Lecture Notes in Statistics. 164. New York, NY: Springer. xiii, 244 p. (2002).

“This book provides a comprehensive treatment of the design of ... two types of experiments that are extremely popular in practice. The optimal design approach advocated in the book will help ... in setting up tailor - made experiments” (from the cover). Consequently, the main emphasis of this book is on practical applications. While the theoretical background is kept on a moderate level the methodology is illustrated extensively by elaborated examples. The book surveys current research of its author.
In Chapter 1, some basics of optimal designs and blocked experiments are introduced. Chapter 2 provides some more advanced topics in optimal designs while in Chapter 3 the concepts of blocked and split - plot experiments are set up. In the subsequent chapters, optimal designs are considered for particular model specifications: 4. Optimal design in the presence of random block effects; 5. Optimal designs for quadratic regression on one variable and blocks of size two; 6. Constrained split - plot designs; 7. Optimal split - plot designs in the presence of hard - to - change factors; 8. Optimal split - plot designs. Chapter 9 covers two - level factorial and fractional factorial designs. In the final Chapter 10 the results are summarized and some directions of future research are indicated.

Reviewer: Rainer Schwabe (Magdeburg)

MSC:

62K05	Optimal statistical designs
62K10	Statistical block designs
62-02	Research exposition (monographs, survey articles) pertaining to statistics
62K15	Factorial statistical designs

Keywords:

optimal block designs; split-plot designs; random block effects; fractional factorials