Great course for anyone interested in modelling/machine learning. Hands on learning with plenty of assignments: labs (using R), WebWork (just a few), written assignments, a project, and lecture worksheets (iClickers). Material covers a lot but you only get a basic understanding of most of it.

In simple terms, you figure out how to model a bunch of different things. What model to use, how to implement it, how to score how well it does, and how to improve it. You're always working with real life data/problems, and modelling is used in just about every field. STAT 306 isn't too useful by itself as it's so broad, but it's still super applicable to real life.

Don't get overwhelmed. You might think there's a lot of material, and there is, but you never learn anything that is THAT difficult. Just stay on top of it and you'll be fine. Assignments can take a lot of time. Some comfort with R helps

Terrible prof. Midterm average was ~45 and refuses to scale up. Expects you to do a lot of self-studying. Doesn't record lectures and not accommodating for students in different timezones. Lectures were only answering few clicker-questions with little explanation of actual course content.

This course is mostly required for students in the statistics-related field. Make sure to not take this course with this professor. Otherwise, the content itself is really useful for data science and some basic machine learning understanding (regarding regressions).