Introduction to Causal analysis - a Bayesian Networks Approach
The tutorial presents an introduction to basic assumptions and techniques for causal discovery from observational data with the use of graphs that represent conditional independence models. It first presents the basic theory of causal discovery such as the Causal Markov Condition, the Faithfulness Condition, and the d-separation criterion, as well as graphical models for representing causality such as Causal Bayesian Networks, Maximal Ancestral Graphs and Partial Ancestral Graphs. It then presents prototypical and state-of-the-art algorithms such as the PC, FCI and HITON for learning such models (global learning) or parts of such models (local learning) from data. The tutorial also discusses the connections of causality to feature selection and presents causality-based feature selection techniques. Apart from the theory and techniques, the tutorial illustrates the use of causal inference through case-studies of applications of causal discovery algorithms with a focus on applications to biomedical data. Finally, it discusses recently introduced directions in the field, such as the integrative analysis of studies using causal models.