• Accessible level:– Presents the concepts and methods of multivariate analysis at a level that is readily understandable by readers who have taken two or more statistics courses. – Emphasizes the applications of multivariate methods and, consequently, they have made the mathematics as palatable as possible. The use of calculus is avoided. • Organization and approach:– Contains the methodological "tools" of multivariate analysis in chapters 5 through 12. – These chapters represent the heart of the book, but they cannot be assimilated without much of the material in the introductory chapters 1-4. – The approach in the methodological chapters (chapters 5-12) is to keep the discussion direct and uncluttered. Typically, the authors start with a formulation of the population models, delineate the corresponding sample results, and liberally illustrate everything with examples. • An abundance of examples and exercises based on real data – Includes, in some cases, snapshots of the corresponding SAS output. – Examples include: Two-way MANOVA for plastic film data (Example 6.11), Principal component analysis of turtle carapace data (Example 8.4), Factor analysis of consumer preference data (Example 9.9), Discriminant analysis of business school admission data (Example 11.11) and others. Highlights and boxes important results and formulas. • Targeted presentation of key concepts:– Directs students’ attention to essential material. – Examples include: Simultaneous confidence region and intervals in Section 6.2, Multivariate linear regression model in Section 7.7, Sample principal components and their properties in Section 8.3, Classification rules in Section 11.3 and others. • Emphasis on applications of multivariate methods. • A clear and insightful explanation of multivariate techniques. • Ample student assistance in navigating difficult topics – Examples include: – Simple numerical calculations to illustrate one-way MANOVA (Example 6.8) – K-means clustering (Example 12.13) and correspondence analysis (Example 12.18) – A clear distinction between population models and the corresponding sample results in all the methodological chapters – Many real data based examples with accompanying graphics and/or computer output (Example 1.8 Linked scatter plots and brushing with Paper Quality Data, Example 6.11) – Two-way MANOVA with Plastic Film Data, Example 10.5 – Canonical correlation analysis of Job Satisfaction Data, Example 12.15 – Multidimensional scaling of Public Utilities Data, and others) – Several “Strategy” and “Final Comments” sections to tie together chapter material (A Strategy for the Multivariate Comparison of Treatments, Perspectives and a Strategy for Factor Analysis, Final Comments-Nonhierarchical (clustering)). – Long and difficult proofs of important results have been relegated to a website.
Les mer