Saville D.J., Wood G.R. Statistical Methods: The Geometric Approach

Springer, 1991. – 561 p. – ISBN: 0387975179, 9780387975177This book presents a novel exposition of the subjects of analysis of variance and regression. The key feature is that these tools are viewed in their natural mathematical setting, the geometry of finite dimensions. Geometry clarifies the basic statistics and unifies the many aspects of analysis of variance and regression.
The Authors
To introduce ourselves, Dave Saville is a practicing statistician working in agricultural research; Graham Wood is a university lecturer involved in the teaching of statistical methods. Each of us has worked for sixteen years in our current field.Basic Ideas: Introduction: The Geometric Tool Kit. The Statistical Tool Kit. Tool Kits At Work.- Introduction to Analysis of Variance: Single Population Questions. Questions About Two Populations. Questions About Several Populations. Orthogonal Contrasts: Class Comparisons. Factorial Contrasts. Polynomial Contrasts. Pairwise Comparisons.- Introducing Blocking: Randomized Block Design. Latin Square Design. Split Plot Design.- Fundamentals of Regression: Simple Regression.- Polynomial Regression.- Analysis of Covariance.- General Summary. Appendices: A: Unequal Replications. Two Populations. B: Unequal Replications. Several Populations. C: Alternative Factorial Notation. D: Regression Through the Origin. E: Confidence Intervals. T: Statistical Tables. References. Index.