This course provides a rigorous introduction to regression analysis, with an emphasis on developing both statistical understanding and practical modeling skills. In addition to covering the core material in regression, I will regularly highlight connections between classical statistical ideas and modern machine learning, including deep learning, reinforcement learning, and large language models, with the goal of helping students understand how foundational ideas in regression continue to appear in contemporary data science and artificial intelligence. These connections are intended to provide broader perspective. More advanced machine learning methods will be studied systematically in my Data Mining course [Fall 2026, 16:960:588].
Evaluation: Midterm Exam 30%, Final Exam 40%, and Course Project 30%. Bonus homework 25%. (Total 125%)
LLM Policy: LLMs permitted for learning and homework; prohibited during exams (both closed-book); students remain responsible for understanding everything they use; project use permitted but must be disclosed.
Homework: all homework will count towards bonus points. You are highly encouraged to do the homework since the exams will be closed book exam.
Project: The course project will be completed in groups of up to three students. Each group will carry out a data-analysis project on a real-world dataset applying regression and related statistical modeling tools to a problem of their choice or a more theoretical-focused open problem project from related fields. The project grade will be based primarily on a final poster presentation, during which each group will present the problem, data, methodology, results, and conclusions of its analysis. All group members are expected to contribute meaningfully to the project and to participate in the final presentation. Further details regarding project expectations, poster format, and evaluation criteria will be provided during the semester.
Attendence: Before the era of AI, it is for sure the easiest way to learn by attending lectures. Now, the easiest way is to use AI to figure out confusion places while attending lectures :)