It is well known that correlation does not necessarily imply causation. In this course, we will ask what is a causal parameter, and how can we estimate such parameters (and under what assumptions). Basic causal inference concepts: Defining a causal parameter (for example the average causal effect), assumptions for identification, randomization, confounding, and selection bias. Using directed acyclic graphs to describe the assumptions. Nonparametric and parametric estimation methods: The propensity score, regression, matching, inverse probability weighting (IPW) etc. Variable selection based on a given graph. Additional topics if time permits and according to the interest in the classroom (for example, instrumental variables and mediation).