Analysis of Messy Data vol 2: Nonreplicated Experiments

About this book

This practical tool for statisticians offers techniques and methods for analyzing non-standard or messy data sets that arise from experimental design situations. Topics discussed include analysis of variance techniques, such as one- and two-way analyses of variance and multiple-comparison procedures. The book introduces each topic with several examples, follows up with a more theoretical discussion, and concludes with a case study. It emphasizes the distinction between design structure and the structure of treatments, and focuses on practical implementation, including computers, with several available statistical packages, including SAS, BMD and SPSS.

Contents

Analyzing Two-Way Treatment Structures with One Observation Per Treatment Combination. The Multiplicative Interaction Model. More on the Analysis of Multiplicative Interaction Models. Half-Normal Plots. Analyzing a Two-Way Treatment Structure in a Split-Plot Design with No Replications . A Three-Way Treatment Structure with No Replications. 2n Factorial Treatment Structures. Blocking 2n Factorial Treatment Structures. Fractional Replications of 2n Factorial Treatment Structures. Polynomial Model Approximations. Quadratic Response Surface Models. Appendices. References . Index

Customer Reviews