Topic: Graphical Models and Bayesian Networks (with R)
Date and time:
June 3, 2021 (11.00 – 16:00, Helsinki time) and June 4, 2021 (11.00-14.00, Helsinki time)
Instructor: Søren Højsgaard, Department of Mathematical Sciences, Aalborg University, Denmark
Goals:
- Graphical models as a framework for modelling associations in multivariate data.
- Dependency graphs and conditional independence restrictions – the components of graphical models.
- Evidence synthesis and probability propagation with Bayesian networks (BNs) using the gRain package.
- A look under the hood of BNs to understand mechanisms of probability propagation.
- Learning BNs from data using the bnlearn package.
- Learning BNs from data using graphical log-linear models in the gRim package.
- Some classical models viewed from a graphical models perspective
Prerequisites:
A working understanding of log-linear models for contingency tables will be very helpful. R will be used for illustration and exercises.
Literature:
Højsgaard, S.; Edwards, D.; Lauritzen, S. (2012): Graphical models with R, Springer.
