ABSTRACT
Hierarchical data structures are regularly encountered in the social and behavioral sci-
ences since measurement often takes place at different levels of collection. A synonymous
term is “multilevel” data meaning that the data represent different levels of aggregation for
the subjects of study. We will use both terms herein since both are widely used across many
social science literatures. A major advantage to the Bayesian paradigm is that these mul-
tilevel/hierarchical models are described and estimated in a very clean and direct manner
with distributional statements.