ABSTRACT
This chapter provides introductions to Bayesian data analysis, model comparison, multilevel models and graphical causal models. Bayesian data analysis provides a way for models to learn from data. Bayesian data analysis has been worked on for centuries. Information criteria are comparatively very young and the field is evolving quickly. Fields as diverse as educational testing and bacterial phylogenetics depend upon routine multilevel models to process data. Grasping the concept of multilevel modeling may lead to a perspective shift. Suddenly single-level models end up looking like mere components of multilevel models. The implications and tests depend upon the details. Newton’s laws of motion for example precisely predict the consequences of specific interventions.
