ABSTRACT
While the problems highlighted in each of the following sections can be considered as typical of the situations considered in applied health economics, they are far from representing an exhaustive set: in real applications, there are countless subtleties and nuisances that need to be addressed specifically. In particular in the Bayesian approach, this requires a careful specification of the model to be used, mainly in terms of the prior distributions, but also in terms of the possible correlation levels among the observed and unobserved random variables.
