Graphical Models in Statistics

What it is about

In this module you will learn statistical models whose conditional independencies are described by graphs. The focus is on continuous distributions (in particular the multivariate normal distribution), undirected graphical models (Gaussian models) and directed acyclic graphs (Bayesian networks). By the end you will be able to represent dependency structures in data with graphical models and select appropriate model classes.

What you will be able to do

• create graphical models for multivariate data
• characterize dependency structure with Gaussian graphical models or Bayesian networks
• explain differences between classes of graphical models
• suggest suitable graphs for modeling specific datasets

What the module consists of

• VorlesungIntroduction and derivation of theoretical concepts; proofs and illustration with examples
• ÜbungDeepening of theory through data examples on the computer with R

Teaching method

• VorlesungIntroduction of theoretical concepts and illustration with practical examples
• Übungen am ComputerDeepening of theory through practical data analyses in R; support by electronic material