Bayesian Methods in Health Economics

Introduction to Bayesian inference 59

required inference using simulation methods. Among these, one of the most

important class of algorithms is represented by Monte Carlo (MC) methods.

The basic idea behind MC integration is that instead of performing calcu-

lation analytically, we can compute an approximate result, based on a large

number of simulations from the model being investigated. The underlying as-

sumption is that the probability distributions involved in the model are all

known.

Suppose for instance that we know the functional form of the posterior

distribution for the parameter of interest θ. We can draw samples from this

distribution θ