The modelling is carried out in a Bayesian framework. The
background to the Bayesian method is detailed in
Chapter 
. There has been much interest in
Bayesian methods in the recent past. Much of this interest stems
from the fact that the computational power is now readily
available to make real Bayesian models tractable. In order to
sample from the posterior distributions of random variables Markov
Chain Monte Carlo (MCMC) is used. Some of the important issues
surrounding MCMC are discussed. These issues were of a real
practical concern when implementing the models described later in
the thesis.