MATH5806 is a Mathematics Level V course. See the course overview below.

Units of credit: 6

Prerequisites:

Cycle of offering: Course not offered every year - contact School for more information.

Graduate attributes: the course will enhance your research, inquiry and analytical thinking abilities.

More information: this recent course handout (pdf) contains information about course objectives, assessment, course materials and the syllabus. (This pdf will usually be updated by the end of the first week of the semester

The Online Handbook entry contains up-to-date timetabling information.

If you are currently enrolled in MATH5806, you can log into the My eLearning Vista instance of this course.

This course is intended to introduce students to modern regression models, and to give experience in appreciating the issues and computing methods needed for applications to real data.

The material begins with familiar normal-theory least-squares regression, and an examination of diagnostic and variable selection methods for simple and multiple regression. Next comes generalized linear models, well-established as the natural regression methods for non-normal responses, whose chief applications are to binary, ordered categorical or count data. Connected to all this material is the large, still developing topic of shrinkage and smoothing methods, including ridge regression, smooth function regression, and penalized methods. If time permits, other relevant special topics such as generalized additive models and mixed models will be discussed.