STAT 432

STAT 432 develops the mathematical and practical foundations of statistical learning with R and Python.

Basics of Statistical Learning

Instructor
Ruoqing ZhuEmail: rqzhu@illinois.edu
Teaching assistant
Chenyu ZhangEmail: chenyuz9@illinois.edu
Office hours
Instructor: Friday, 3:00 to 4:00 p.m.Instructor office: 137 CABTA: Monday, 2:00 to 4:00 p.m. (Zoom)
Class meeting
Tuesday and Thursday12:30 to 1:50 p.m.2039 Campus Instructional Facility

Read the Syllabus

New Design of the Course

The course is organized around four priorities.

Materials from the previous version of the course are available here.

In-class discussion
Tuesday classes center on student questions, Group Discussion, and Present and Challenge.
AI coding agents
You must have an AI coding agent available. Using it is optional unless a homework question explicitly asks you to test a skill.
Quizzes and final project
The course includes four 30-minute, closed-book quizzes and a final project.
Understanding first
Lectures and homework emphasize explaining why methods work, not only producing answers.

Discussion Sessions

The discussion cycle begins after Thursday's lecture and continues in Tuesday's class. Student questions provide the material for Group Discussion, Present and Challenge, and quizzes.

  1. Prepare and Submit Discussion Questions

    After Thursday's lecture, write and submit one question in your course GitHub repository.

  2. Discuss Questions in Groups

    Work through selected questions with your group and compare possible answers.

  3. Present and Challenge

    Assigned teams present their reasoning, students from other teams may challenge the answer, and the class rates presenting teams and challengers.

  4. Four Quizzes

    Complete four 30-minute, closed-book quizzes during Tuesday classes.

Announcements

Weekly reminders, discussion updates, quiz notices, and schedule changes will appear here.

  1. Week 6 lecture notes are ready

    Classification Error and Evaluation now includes two lecture notes on Bayes decisions, probability losses, bias and variance, and evaluating logistic regression with confusion matrices and ROC curves. Both notes include R and Python examples.

  2. Homework 04 is ready

    Homework 04 for Lasso and Variable Selection is now available with R and Python solutions and downloads. Homework 04 and the Week 4 discussion question are due Sunday, September 20, at 11:59 p.m. Central Time.

  3. Week 5 materials are ready

    K-Nearest Neighbors now includes both lecture notes, the revised five-question Homework 05, R and Python solutions, and downloads. Homework 05 and the Week 5 discussion question are due Sunday, September 27, at 11:59 p.m. Central Time.

  4. Lecture materials through Week 4 are ready

    Lecture materials for Weeks 1 through 4 and homework materials for Weeks 1 through 3 are now available. Homework 04 will be posted after review.