Causality

Spring semester 2020

General information

Lecturer Christina Heinze-Deml
Assistant Loris Michel
Lectures Wednesday 10-12 HG E 1.1 >>
Course catalogue data >>

Course content

In statistics, we are used to search for the best predictors of some random variable. In many situations, however, we are interested in predicting a system's behavior under manipulations. For such an analysis, we require knowledge about the underlying causal structure of the system. In this course, we study concepts and theory behind causal inference.

Announcements

  • March 17th 2020: From now on, all announcements will be posted in Moodle.
  • March 11th 2020: The lecture recordings can be found in Moodle.
  • March 9th 2020: Starting this week, the lectures will be recorded. Since I cannot be in Zurich this Wednesday (March 11th), this week's lecture will be pre-recorded and will be available *only* electronically. I will send you the information where to find the video on Wednesday.
  • February 10th 2020:
    • A few times during the course, there will be in-class exercise sessions instead of a normal lecture. During those sessions, we will work with jupyter notebooks and R. Please make sure to install jupyter and the required R packages beforehand. Installation instructions are given here.
    • We will be using the ETH EduApp during the lectures for clicker questions. Please install it on your phone or tablet (iOS, Android). If this is not possible, you can also access the EduApp via the Web App if you bring a laptop to class.

Course materials

Week Topic
Week 1 Introduction
Week 2 Graphical models
Week 3 Causal graphical models
Week 4 Causal models and covariate adjustment
Week 5 Exercise session: Please see Moodle for further information.
Week 6 Covariate adjustment
Week 7 Instrumental variables and transportability
Week 8 Counterfactuals, potential outcomes and estimation
Week 9 No class (Easter break)
Week 10 Exercise session: Please see Moodle for further information.
Week 11 Towards structure learning
Week 12 Constraint-based causal structure learning
Week 13 Score-based causal structure learning and restricted SEMs
Week 14 LiNGAM and Invariant Causal Prediction
Week 15 Exercise session: Please see Moodle for further information.

In-class exercises

A few times during the course, there will be in-class exercise sessions instead of a normal lecture. During those sessions, we will work with jupyter notebooks and R. These are provided in this Github repository.

Take-home exercises

If you are a PhD student who needs ETH credit points, the submission of the solutions is mandatory. If this applies to you, please email your solutions to Loris Michel or place them in the corresponding tray in HG J 68. Students who need ECTS credit points have to take the exam.

Exercises Solutions Due date
Series 1 Solutions 1 March 11th 2020
Series 2 Solutions 2 March 25th 2020
Series 3 (updated 01/04) Solutions 3 April 8th 2020
Series 4 Solutions 4 April 22nd 2020
Series 5 Solutions 5 May 20th 2020

Literature