Bayesian methods

TL;DR: In this paper, the authors present a survey of Bayesian methods for health-care evaluation, focusing on the following: 1.1 What is probability? 2.2 Random variables, parameters and likelihood.

TL;DR: The authors compare the performance of multilevel models when few countries are available and find that maximum likelihood estimates and confidence intervals can be severely biased, especially in models including cross-level interactions, while the Bayesian approach proves to be far more robust and yields considerably more conservative tests.

TL;DR: This work points out problems with the assessment of country effects that appear not to be widely appreciated, and develops arguments using Monte Carlo simulation analysis of multilevel linear and logit models.

TL;DR: This chapter discusses Bayesian analysis for simple models, which focuses on the case for hierarchical modeling, and its applications in the Social Sciences and Simulation Based Bayesian Analysis.