Causality

What it is about

You engage with concepts and methods of causal inference: from probabilistic and graph-theoretic foundations through structural models to modern algorithms for causal discovery and estimation of causal effects. In the end you can judge whether and how causal conclusions are possible from given data and assumptions, select appropriate methods and apply them in practice.

What you will be able to do

• Understand the basic concepts of causality and probabilistic graphical models
• Know Neyman–Rubin and structural equation models
• Apply interventions, do‑Calculus and counterfactuals
• Choose and apply methods for estimating causal effects (Matching, Propensity Score, Doubly Robust, IV, Diff‑in‑Diff)
• Assess causal discovery from data with suitable algorithms
• Conduct sensitivity analysis for assumptions

What the module consists of

• VorlesungDelivery of the theoretical foundations of causal inference
• Übungen / wöchentliche ÜbungssitzungenSelf-study, consolidation of concepts; presentation and discussion of solutions
• Live‑Coding / MedienDemonstration and practical application of algorithms

Teaching method

• Lecture combined with exercises for self-studyConcepts are introduced in the lecture; exercises deepen understanding through hands-on application
• Weekly exercise sessionsPresentation and discussion of exercise and solution approaches to reinforce understanding