While the Bayesian framework provides an attractive approach to model calibration
and uncertainty analysis, the computational effort required to implement
Bayesian procedures can hinder their application. To this end, Markov chain Monte
Carlo (MCMC) sampling provides an efficient and robustway to implement Bayesian
methods. The aim of MCMC sampling is to generate samples from the posterior
distribution of the model parameters by simulating a random process that has the
posterior distribution as its stationary distribution (Marshallet al., 2004). In this