Course Info
Format of Lectures
We will adopt a blended learning approach. Slides, readings, class exercises, datasets and lecture videos will be stored in the VULA resources folder. Students will be expected to do a large degree of self-study. Each section will require students to implement the methods using R. Students may be asked to present their implementation to the class in discussion sessions. Face-to-face sessions will be scheduled for Mondays and Wednesdays 4 to 6 pm in departmental seminar room 4.26. During these sessions, we will review the main content, answer questions and review practical work.
| Day | Time | Location | |
|---|---|---|---|
| Lectures | Mon & Wed | 4:00 pm - 5:45 pm | Seminar room 4.26 (Quiet room) |
Recommended Textbook
AJ Izenman, “Modern Multivariate Statistical Techniques”, Springer, 2013.
· https://link.springer.com/book/10.1007/978-0-387-78189-1
· https://www.amazon.com/Modern-Multivariate-Statistical-Techniques-Classification/dp/0387781889
Assignment
Students will be required to research the application of modern multivariate methods to different areas of application. They will need to focus on methodology, application, programming and interpretation. They will submit a 10-page summary report.
Duly Performed Requirements
Attendance at all lectures and timely submission of all class exercises and assignments. There will be a late submission penalty for the assignment and you will only be allowed to miss at most 4 hours of lectures out of 24 hours (2 days worth of lectures) without a proof of medical note.
Assessment
Assignment 50%
Open book take home exam 50%
A pass mark of 50% is required overall, with a 40% sub-minimum on each of the assignment and exam component.
Important dates
- 12 Feb: Classes begin on Monday
- 12 Feb: Assignment release
- 19 Feb: Course drop ends!
- 26 Feb: Assignment topic submission
- 4 March: Assignment proposal submission
- 13 March: Draft report
- 18 March: Peer review
- 20 March: Final report
- 22 March: Github repo + presentation + slides
Load Shedding/Student Protests
In the event of load shedding, student protests-related events that might affect student attendance in lectures, I will make the necessary announcements in advance how to proceed with the affected lecture. This might mean that we will meet online on MS Teams or you will be watching a video recording of the lecture that will be recorded by me.