Explores computationally-intensive methods in statistics. Topics covered include Fundamentals of Optimization, Combinatorial Optimization, EM algorithm, Monte Carlo simulation, Markov Chain Monte Carlo methods. Lab work is carried out using R or Python.
4
UnitsOptional
Grading1, 2, 3
PasstimeGraduate students only
Level LimitLetters and science
CollegeThis class was a mess. The professor just read off the slides, never explained anything clearly, and didn't seem to care if we understood. Grading felt random, and office hours were useless. I came in hoping to learn stats, but mostly left confused and frustrated. Wouldn't recommend at all.
Yu leaves much to be desired in their teaching approach. Classes often felt disorganized, with a lack of clear objectives or structured material. Key concepts were often rushed through or skipped entirely, making it challenging to understand the course content fully.
Best lecturer in pstat department.
I took this class as an undergrad. I found this class pretty interesting. The grading is 45% hw, 45% project, 10% lecture scribe. You're expected to use LaTeX in RMarkdown for homework and LaTeX for scribing (only one lecture per person.) The homework assignments are pretty challenging but you have plenty of time to do them cus they're only 3 of em
Class is easy for a graduate course, a lot of content overlaps with the stuff for PSTAT 131 students, except for the final that has a proofs section a little bit harder but still doable for a grad student. The final project's instructions were vague but my final project was dogsh*t and got an A- so he's chill. If u want easy A, take coburn instead
Definitely avoid if you can. Unfair exams, more focused on confusing and tricking students than assessing their knowledge of the material