University of Minnesota
Course Information for Stat 8311, Linear Models
Hours: M, 3:35-4:25 213 Vincent Hall; WF, 2:30-3:20, 313 Vincent Hall
Fall Semester, 2006

General Information

The instructor is S. Weisberg, 312 Ford Hall, 625-8355. Office Hours: Thursday 2-3, or by appointment. I can be reached via email at sandy@stat.umn.edu. The TA is Yingwen Dong, her office hour is Tuesday 10-11 in 352 Ford, or by appointment, (ywdong@stat.umn.edu).

Please note the class will meet at at 3:35 on Mondays in 213 Vincent Hall and 2:30 Wednesday and Fridays in 313 Vincent Hall.

There will be no class on Monday, October 2.

There will be no class on Friday, October 27, but will meet both at 2:30 and at 3:35 on Monday, October 30.

Content and prerequisites

This course is part of the core Ph.D. program in the School of Statistics and in the Division of Biostatistics. The desirable prerequisites for the course are: (1) a year of mathematical statistics at the 5xxx level or higher; (2) courses in regression analysis and experimental design at the 5xxx level or higher, and (3) a course in linear algebra at the undergraduate level or higher, although we will begin the course with a review of the required linear algebra from a coordinate-free perspective.

This course is offered in 2006 for the last time. The material covered in this course will be dispersed to several courses in the newly revised statistics Ph.D. core curriculum.

Books

We will be using two written sources:

• For the first part of the course, we will use course notes that will be provided in class and will be available on the web.
• Pinheiro, J. and Bates, D. (2000). Mixed-Effects Models in S and S-plus. New York: Springer. This book will be used in the last third of the class. This book is useful if you ever plan to apply mixed models to real data.

If you are unfamiliar with R, you might want to buy a book such as W. Venables and B. Ripley (2002), Modern Applied Statistics with S, New York: Springer, although it is not required.

Class homepage

http://www.stat.umn.edu/~sandy/courses/8311. Assignments and handouts will be posted on the homepage.

Homework

There will be frequent homework assignments, and we will occasionally go over solutions to homework problems. Homework will then be collected and graded. Students may be asked to present solutions on the board. Collaboration on homework is specifically permitted and encouraged.

Grading

There will be two exams, an in-class midterm (35%) scheduled for Friday, November 3, and a final (50%) that may be either in-class (10:30am-12:30pm Friday, December 15) or take home; I will decide after the midterm exam. Homework counts for 15% of the course grade.

Academic integrity is essential to a positive teaching and learning environment. All students enrolled in University courses are expected to complete coursework responsibilities with fairness and honesty. Failure to do so by seeking unfair advantage over others or misrepresenting someone else’s work as your own, can result in disciplinary action. The University Student Conduct Code defines scholastic dishonesty as follows:

Scholastic Dishonesty: Scholastic dishonesty means plagiarizing; cheating on assignments or examinations; engaging in unauthorized collaboration on academic work; taking, acquiring, or using test materials without faculty permission; submitting false or incomplete records of academic achievement; acting alone or in cooperation with another to falsify records or to obtain dishonestly grades, honors, awards, or professional endorsement; altering forging , or misusing a University academic record; or fabricating or falsifying data, research procedures, or data analysis.

Within this course, a student responsible for scholastic dishonesty can be assigned a penalty up to and including an ``F" or ``N" for the course. If you have any questions regarding the expectations for a specific assignment or exam, ask.

Computing

While the emphasis in this course is on theory, not application, you will occasionally have data problems assigned, particularly in the last third of the course. Computing will be done using R with the package lme for mixed models. R is available on the School Linux network, and can be downloaded for your own PC or Macintosh for free from www.r-project.org. If you prefer and have access, you can use SAS for computing as well.

This material is available in alternative formats upon request. Please contact School of Statistics, Ford 313, 625-7300.