Introduction to Causal Inference in Time Series
Introduktion till kausal inferens i tidsserier

FRT295F, 7.5 credits

Valid from: Spring 2023
Decided by: Maria Sandsten
Date of establishment: 2023-03-16

General Information

Division: Automatic Control
Course type: Third-cycle course
Teaching language: English

Aim

The goal is to 1) provide students with an overview of modern causal inference methods, and 2) provide them with knowledge of when and how to apply such methods.

Goals

Knowledge and Understanding

For a passing grade the doctoral student must

• demonstrate understanding of the causal modeling formalism introduced in the course
• demonstrate knowledge of the differences between observational and interventional data
• demonstrate knowledge of the connection between experiments and causal models
• demonstrate knowledge of the connections between causal modeling and control theory
• demonstrate understanding of causal modeling in time series and how it differs from other types of causal modeling

Competences and Skills

For a passing grade the doctoral student must

• be able to apply the causal identification methods introduced in the course
• be able to apply the graphical methods introduced in the course
• be able to solve applied causal inference problems studied in the course

Judgement and Approach

For a passing grade the doctoral student must demonstrate understanding of the differences between classical statistical methods and causal inference methods

Course Contents

Topics include: - foundations of causal inference (defining causal models and causal effects, observational and interventional data, connections to experiments/randomized trials) - identifiability and estimation of causal effects - graphs as representations of causal systems - causal inference in time series models and connections to control theory

Course Literature

Jonas Peters, D. & Schölkopf, B.: Elements of Causal Inference. The MIT Press, 2017. ISBN 9780262037310.
Open access e-book is available online.

Instruction Details

Types of instruction: Lectures, exercises

Examination Details

Examination format: Written assignments
Grading scale: Failed, pass
Examiner:

Admission Details

Assumed prior knowledge: basic statistics, probability theory, and linear algebra

Course Occasion Information

Contact and Other Information

Course coordinator: Søren Wengel Mogensen <soren.wengel_mogensen@control.lth.se>