Statistics 521 - Multivariate Analysis (Spring 2004)
Instructor: Dr. Chris Williams Office: Room 414 Brink Hall Phone: 885-2802 (direct) or 885-2929 (Division office) Meeting times: MWF 1:30-2:20 Admin 227 Office Hours: MWF 2:30-3:20 or by appointment. Prerequisites: Stat 401 or equivalent coursework. Text: Applied Multivariate Methods for Data Analysts by Dallas E. Johnson, Kansas State University email: chrisw@uidaho.edu webpage: http://www.uidaho.edu/~chrisw/stat521/. The webpage will contain announcements, summaries of lectures, lists of assignments with due dates, and other information. Objectives: Multivariate analysis is concerned with analysis of data consisting of several measurements on each observation. We will cover a number of ways to analyze such data, some of which are exploratory in nature, while others are used in confirmatory analyses. The course objective is for you to develop an understanding of the various methods of multivariate analysis and the ability to apply appropriate multivariate methods to your own research data. Course Outline: 1. Introduction to multivariate data and SAS. 2. Sample correlations. 3. Visualizing multivariate data, SAS Proc INSIGHT. 4. Eigenvalues and eigenvectors. 5. Principal components analysis. 6. Factor analysis. 7. Discriminant analysis. 8. Logistic regression methods. 9. Cluster analysis. 10. Mean vectors and covariance matrices. 11. Multivariate analysis of variance. 12. Prediction models and multivariate regression. We will use the SAS computer package throughout the course. Grading: Homework: 20% Test 1 25% Test 2 25% Project 10% Final 20% Wednesday, May 12 at 1pm