Computation in Bayesian econometrics: An introduction to Markov chain Monte Carlo

In this paper the recent developments in computational Bayesian methods are reviewed. Specifically, the Monte Carlo tools of Gibbs sampling and Metropolis-Hastings sampling are introduced and their use illustrated in the context of two important econometric models: the binary data probit model and the Markov switching regression model. With the interest of the applied researcher in mind, the paper contains full details, including pseudo-computer code for the examples discussed.