Exponential family and generalized linear models including logistic and Poisson regression, nonparametric regression, including kernel, spline and local polynomials, and generalized additive models. Other topics as time allows: regularization, neural networks, and support vector machines. Emphasis will be on concepts and practical applications.
4
UnitsOptional
Grading1, 2
PasstimeNone
Level LimitLetters and science
CollegeLecture
The professor is a very very nice person. However, the course is taught superficially and moves very slowly. (6 weeks on glm, 2.5 weeks on ridge/lasso, 1.5 weeks on nonparametric methods) I also need to do a lot of repeated and really boring practice problems to do well on exams.
Clearly passionate about the subject but is an extremely harsh grader and stickler for notation. Expect to spend lots of time in office hours and study groups if you want to pass. Grading 15% quizzes (unlimited attempts), 20% homework, 20% midterm, 45% final
Professor Meiring is a very nice person, but it felt like she was juggling many things at once. It felt difficult to get more than a surface-level understanding of the material and the final was worth 45% which made the class stressful. Luckily, the midterm and final were similar to the practices (which are previous exams) which was helpful.
She is decent
Course had some interesting concepts, but it wasn't taught practically. Textbook barely used here. Lectures could have concrete analysis after drawing figures in lecture instead of more sketches. Quizzes needed to be worth more too!
Does not use a textbook. Setup was rough. Exams are tough. I thought I'd get an A.