Anova and Ancova - 9780470385555

This new edition continues to provide a contemporary look at the nature of GLM (general linear model) analyses, describing how to implement such analyses throughout the experiment design process, from data examination to the testing of hypotheses. The book begins with a brief history of the separate development of ANOVA and regression analyses, and then goes on to demonstrate how both analyses are incorporated into the understanding of general linear models (GLM). The chapters that follow are clearly organized by the nature of the experimental design and its analyses, detailing conventional statistical concepts of ANOVA and ANOVA and interpreting them in GLM terms. The book proceeds to cover the main single- and multi-factor designs as they relate to ANOVA and ANCOVA. All chapters have been revised, as each area of coverage now concludes with discussion of tests of main effects and type 1 error issues. Furthermore, a new chapter on hierarchical models introduces the use of this technique to methods in experimental psychology. Additional topics that have been expanded upon and added include: different approaches to carrying out the simple effect analyses and pairwise comparisons (particularly with regard to related and repeated measure analyses), the power of the different approaches to the different effect analyses, optimal experimental designs, a review of Wilcox’s arguments, normality violations and their consequence for experimental analyses, and the issue of inflated Type 1 error due to multiple hypotheses testing.