|Campus Map | Phonebook | Calendars | A-Z Index|
STAT 571A/MATH 571A − Advanced Statistical Regression Analysis
Prerequisite(s): MATH 363 or equivalent; and MATH 310 or MATH 313, or equivalent.
Description: Regression analysis including simple linear regression and multiple linear regression. Matrix formulation and analysis of variance for regression models. Residual analysis, transformations, regression diagnostics, multicollinearity, variable selection techniques, and response surfaces. Students will be expected to utilize standard statistical software packages for computational purposes.
This course in Advanced Statistical Regression Analysis provides graduate students in statistics, biostatistics, mathematics, and related disciplines with an in-depth course of study in regression models and associated data analyses. It explores advanced regression topics, including regression diagnostics and simultaneous inferences, and other miscellaneous topics.
Fall 2017The course will meet Tuesdays and Thursdays from 2:00 pm - 3:15 pm in Medical Research Bldg. (MRB), 1656 E Mabel St. (Bldg. no. 241), room 102.
The textbook is Applied Linear Regression Models, 4th Edition (2002) by Michael Kutner, Christopher Nachtsheim, and John Neter. Additional online resources are available at the book's Student Download Site. The course syllabus gives complete information.
AttendanceStudents are expected to attend class. If important circumstances prevent this, it is the student's responsibility to find out what was covered in class, what was assigned for reading or homework, and what special announcements (if any) were made.
Homework Assignments - Fall 2017Homeworks are based on exercises from the textbook.
Homeworks are due as assigned. No exceptions.
These assignments are subject to revision with prior notice. Complete data for the problems are available in the Textbook's CD or online.Textbook Date due Chapters Exercises ------------------------------------------------- Sep. 12 1 1.5, 1.19, 1.20a*d* 1.21*, 1.29, 1.30 Oct. 3 2-3 2.5a*b*c*d*, 2.6a*b*c*d*, 2.6e(part 'b' only)*, 2.14a*b*d*, 2.18, 2.24a*b*c*d*, 2.33bc, 2.42*, 3.4c*d*f*, 3.4e(plot only)*, 3.4g(use Brown-Forsythe), 3.5c*d*f*, 3.5e(plot only)*, 3.5g(use Brown-Forsythe), 3.13a*b*, 3.17(in b, use maximum likelihood)* 3.18cd, 3.20 Oct. 17 4-5 4.1, 4.3*, 4.5ab, 4.7*, 4.16*, 4.17*, 5.1, 5.4*, 5.12*, 5.23*, 5.25*, 5.30 Oct. 26 1-5 Mid-Term Exam (available Oct. 24) Nov. 7 6-7 6.2, 6.5abcdf, 6.9c*, 6.10a*b*, 6.11*, 6.15b*c*e*, 7.4*, 7.5*, 7.6*, 7.11, 7.12, 7.24, 7.25* Nov. 14 8-9 8.15, 8.17, 8.19*, 8.21, 9.10b*c*, 9.11*, 9.13bc, 9.14 Dec. 5 10-11 10.5, 10.8, 10.9abceg, 10.10a*b*d*f*, 10.16*, 11.6acdef, 11.7a*d*e*f*, 11.10a*, 11.10d*, 11.25 Dec. 12 Comprehensive Final Exam * Student solution manual answer available
Textbook Errata List.
PDF of handwritten notes for components of sampling distribution for b1 from Chapter 2.
Sample R code for PRESS plot with data from Chapter 9, Table 1.
A technical report giving Tables of P-values for t- and Chi-square distributions.
Stigler's 1980 article discussing the Law of Eponymy.
Selected online encyclopedia entries on regression analysis (access requires the University Library's online subscription):
Formulas and identities for calculating the sample variance and associated sums of squares. Background on Sir Francis Galton. Galton's concept of regression to the mean. The Method of Least Squares for linear regression. Aspects of Quadratic Forms, including degrees of freedom for mean squares in linear (regression) models. For those who are interested, a review of Simpson' Paradox. An introduction to Kimball's Inequality.
Appendix A Notes (Short) R intro. Notes Chapter 1 Notes Chapter 2 Notes Chapter 3 Notes Chapter 4 Notes Chapter 5 Notes Chapter 6 Notes Chapter 7 Notes Chapter 8 Notes Chapter 9 Notes Chapter 10 Notes Chapter 11 Notes
General R Language Downloads/Links
Suggested reading: The R Guide, ver. 2.5
R language comprehensive archive
R language FAQ page
R language online introduction
- Read the sections of the text and view pertinent videos to be covered prior to the class.
- Attend class regularly. Arrive on time.
- Ask questions if you don't understand an issue.
- Attempt to do all assigned homework and writing assignments. (Come to Office Hours if encountering difficulty.)
The views and opinions expressed in this page are strictly those of the page author. The contents of the page have not been reviewed by the University of Arizona.