Planning, Construction, And Statistical Analysis Of Comparative Experiments

A valuable guide to conducting experiments and analyzing data across a wide range of applications
Experimental design is an important component of the scientific method. This book provides guidance on planning efficient investigations. It compiles designs for a wide range of experimental situations not previously found in accessible form. Focusing on applications in the physical, engineering, biological, and social sciences, Planning, Construction, and Statistical Analysis of Comparative Experiments is a valuable guide to designing experiments and correctly analyzing and interpreting the results. The authors draw on their years of experience in the classroom and as statistical consultants to research programs on campus, in government, and in industry. The object is always to strike the right balance between mathematical necessities and practical constraints.
Serving both as a textbook for students of intermediate statistics and a hands-on reference for active researchers, the text includes:
A wide range of applications, including agricultural sciences, animal and biomedical sciences, and industrial engineering studies
General formulas for estimation and hypothesis testing, presented in a unified and simplified manner
Guidelines for evaluating the power and efficiency of designs that are not perfectly balanced
New developments in the design of fractional factorials with non-prime numbers of levels in mixed-level fractional factorials
Detailed coverage on the construction of plans and the relationship among categories of designs
Thorough coverage of balanced, lattice, cyclic, and alpha designs
Strategies for sequences of fractional factorials
Data sets and SAS® code on a companion web site
An ideal handbook for the investigator planning a research program, the text comes complete with detailed plans of experiments and alternative approaches for added flexibility.

FRANCIS G. GIESBRECHT, PhD, is Professor Emeritus in the Department of Statistics at North Carolina State University in Raleigh, North Carolina. He earned his PhD in Statistics from the Iowa State University.
MARCIA L. GUMPERTZ, PhD, is a professor in the Department of Statistics at North Carolina State University where she also received her PhD in Statistics.

"…an excellent reference for statisticians and practitioners who would like to gain broad exposure to the tools available for studying relationships between qualitative and quantitative factors…" (Journal of the American Statistical Association, June 2005)
“The level of detail is higher than in most other books on similar topics and therefore makes this one a useful reference tool.” (Short Book Reviews, Vol.25, No.1, April 2005)
"I will instruct statistician reporting to me to get a copy of the book, and will keep the review copy readily available on my shelf…" (Technometrics, February 2005)
"There is a moderate amount of material that is not in other design books…in addition to some tricks of the trade that appear to be new…practitioners…will find the book useful." (Journal of Quality Technology, October 2004)
"...an excellent resource handbook for researchers and statisticians, providing them with the tools necessary to construct better experiments and plan more efficient investigations.” (CHOICE, October 2004)

Preface.
Introduction.
The Completely Randomized Design.
Linear Models for Designed Experiments.
Testing Hypotheses and Determining Sample Size.
Methods of Reducing Unexplained Variation.
Latin Squares.
Split-Plot and Related Designs.
Incomplete Block Designs.
Repeated Teatments Designs.
Factorial Experiments, the 2n System.
Factorial Experiments, the 3n System.
Analysis of Experiments Without Designed Error Terms.
Confounding Effects with Blocks.
Fractional Factorial Experiments.
Response Surface Designs.
Plackett-Burmann Hadamard Plans.
The General Pn and Nonstandard Factorials.
Factorial Experiments with Quantitative Factors.
Plans for Which Run Order is Important.
Supersaturated Plans.
Sequences of Fractions of Factorials.
Multi-Stage xperiments.
Orthogonal Arrays and Related Structures.
Factorial Plans Derived via Orthogonal Arrays.
Experiments on the Computer.