Statistical Learning (2023)

Course Description and Outline

The course presents theory and applications for some important statistical learning (supervised and unsupervised) techniques such as linear and logistic regression, classification and regression trees, random forests and lasso regularization. The course is structured as follows:

1. Linear Models
2. Classification
3. Resampling Methods
4. Model Selection and Regularization
5. Tree-Based Methods
6. Unsupervised Learning

R statistical programming will be used throughout the course. The course is largely based on the textbook “An Introduction to Statistical Learning” by James, G., Witten, D., Hastie, T., and Tibshirani, R. A solid understanding of statistics and econometrics is a prerequisite for this course.

Course Materials and Time Schedule

The course material is provided via ILIAS. You have to register for the course via Zeus and will be automatically added to the ILIAS folder.

The lecture takes place on Thursdays. On Fridays, we work on empirical applications in R. You should bring your laptop!

Prerequisites

Econometrics I (required)

Advanced Econometrics (desirable)

Introductory Literature

An Introduction to Statistical Learning with Applications in R, G. James, D. Witten, T. Hastie and R. Tibshirani, 2^nd ed, Springer, 2021

The Elements of Statistical Learning, T. Hastie, R. Tibshirani and J. Friedman, 2^nd ed, Springer, 2009

Grading

The grading is based on a presentation of programming exercises (20%) and a final exam (80%).