Richard F. Haase is Professor Emeritus and Research Professor in the Division of Counseling Psychology of the School of Education and Fellow of the Institute for Health and the Environment of the School of Public Health, both at the University at Albany of the State University of New York. After completing his Ph.D. in Psychology from Colorado State University he has taught research methods, statistics and data analysis at the University of Massachusetts at Amherst, Texas Tech University and the University at Albany. His interests are in the areas of research methods, univariate and multivariate statistics, and vocational psychology. His work on research methodology and data analysis has appeared in the Journal of Consulting and Clinical Psychology, Journal of Counseling Psychology, Educational and Psychological Measurement, Multivariate Behavioral Research, Applied Psychological Measurement, Environmental Research, and the Journal of Vocational Behavior.

1. Introduction and Review of Univariate General Linear Models2. Specifying the Structure of the Multivariate General Linear Model3. Estimating the Parameters of the Multivariate General Linear Model4. Partitioning the SSCP, Measures of Strength of Association, and Test Statistics in the Multivariate General Linear Model5. Testing Hypotheses in the Multivariate General Linear Model6. Coding the Design Matrix and the Multivariate Analysis of Variance7. The Eigenvalue Solution to the Multivariate General Linear Model: Canonical Correlation and Multivariate Test StatisticsReferences

Multivariate General Linear Models is an integrated introduction to multivariate multiple regression analysis (MMR) and multivariate analysis of variance (MANOVA). Beginning with an overview of the univariate general linear model, this volume defines the key steps in analyzing linear model data, and introduces multivariate linear model analysis as a generalization of the univariate model. The author focuses on multivariate measures of association for four common multivariate test statistics, presents a flexible method for testing hypotheses on models, and emphasizes the multivariate procedures attributable to Wilks, Pillai, Hotelling, and Roy. The volume concludes with a discussion of canonical correlation analysis that is shown to subsume all the multivariate procedures discussed in previous chapters. The analyses are illustrated throughout the text with three running examples drawing from several disciples, including personnel psychology, anthropology, environmental epidemiology, and neuropsychology.