This is a direct application of the Integrated Nested Laplacian Approximation (INLA) framework for approximate Bayesian inference. In this tutorial we examined math achievement scores (
MathAchieve in the
MEMSS library) across schools and individuals as a hierarchical regression problem.
See the knitted RMarkdown notebook here.
We discussed the motivations for different priors and worked on fully utilizing the Initial Data Examination (IDE) as a crucial step to inform modelling choices.