PubH 7405: Biostatistics Regression Fall 2006; 4 credits; A/F or S/N Course information: This course is concerned with the theory and application of appropriate statistical techniques for regression analysis. It is intended as an introductory course for biostatistics graduate students and quantitatively oriented students. Instructor: Dr. Baolin Wu; email: baolin@biostat.umn.edu; Office: Mayo A442; Phone: (612)624-0647; Office hours: Monday/Wednesday 2:00-3:00PM. Prerequisite: Stat 5101 or concurrent registration is required (or allowed) in Stat 5101. It is assumed students have had calculus and are familiar with matrix and linear algebra. Course website: http://www.biostat.umn.edu/~baolin/teaching/ph7405-06F. Textbook: Michael H Kutner, Chris J. Nachtsheim and William Wasserman (2004). Applied Linear Regression Models. 4th edition, McGraw-Hill/Irwin. Additional readings: • Raymond H. Myers (2000). Classical and Modern Regression with Applications. 2nd edition, Brooks Cole. • WN Venables and Brian D. Ripley (2002). Modern Applied Statistics with S. 4th edition, Springer-Verlag. • Sanford Weisberg (1985). Applied Linear Regression. 2nd edition, Wiley. • Fred Ramsey and Daniel Schafer (2002). The Statistical Sleuth. 2nd edition, Pacific Grove, CA: Duxbury. Course grade: The final grade will be based on homeworks, inclass midterm and final exams. Disability Statement: If you have a disability that affects participation in class activities and requirements, please contact the Office of Disability Services (612-626-1333, Suite 180 in the University Gateway Building, 200 Oak Street) and we will work together to accommodate you. 1 Tentative schedule: Week Topics 1 Overview of Probability & Statistics 2 Simple Linear Regression 3 Inference in Regression Analysis 4 Diagnostics and Remedial Measures 5 Simultaneous Inferences & Other Topics 6 Matrix Approach to Regression 7 Multiple Regression - I 8 Midterm Exam 9 Multiple Regression - II 10 Multiple Regression - II 11 Qualitative Predictor Variables 12 Regression Diagnostics 13 Regression Remedial Measures & Validation 14 Autocorrelation in Time Series Data; Introduction to Nonlinear Regression 15 Final Exam 2