Tutorials: There are various tutorial times and locations. Your tutorial is indicated on your timetable. The purpose of the tutorial is to reinforce that which was taught in class. For the most part, relevant practice problems will be considered in the tutorial as well as opportunities to ask questions. The tutorials will be run by a graduate student in Statistics (Celes Ying; email cying@sfu.ca) and the tutorials will begin in week three.
Marking: The marking of assignments and midterms will be carried out by a graduate student in Statistics (Lihui Zhao; email lhzhao@sfu.ca). Lihui has been instructed to be consistent in the marking; sometimes he will be tough, sometimes he will be lenient but he will always be consistent. If you have a problem with the marking, I want you to see Lihui first. If you still have a problem, you can then see me although I will be reluctant to make changes. I will mark the project and the final exam.
Office Hours: Mondays and Wednesdays from 11:30-12:20 in K10539 or by appointment.
Textbook: none
Reference Textbooks: Applied Regression Analysis by Draper/Smith, Applied Linear Statistical Models by Neter/Wasserman/Kutner, Applied Linear Regression by Weisberg
Computing: Accounts will be given out for the Assignment Lab. Students are free to use the statistical package of their choice. The assignment lab supports Minitab, Splus and SAS. The easiest of these to learn is Minitab. A good introduction can be found by going to the minitab link. Celes will provide some computing instruction in the tutorials.
Content: In a nutshell, this course involves fitting hyperplanes to points, assessing the adequacy of the fit and addressing related inferential questions. Although it will not appear so initially, this is arguably the most practical statistics course that you will ever take.
Marking Scheme:
For the purposes of the assignments and the project, I will allow you to work in teams of a maximum of four people per team. When you hand in your work, hand in one package per team and make sure that every team member's name appears on the work. Naturally, there is the possibility that not everyone will contribute equally on assignments and the project, and it is up to you as mature students to make sure that you learn something from the assigned work. For the last week of classes, students will be asked to give short presentations (10-15 minutes) relating to their projects. The project will be an analysis of a real data set that addresses a question of interest and uses the techniques developed in the course. You should start thinking about a topic early in the semester.
Advice: Read your notes regularly. Make sure you don't fall behind as the course builds upon itself.
Here is the bodyfat data.