Bayesian Full Information Analysis of Simultaneous Equation Models Using Integration by Monte Carlo

In their review of the "e;Bayesian analysis of simultaneous equation systems"e;, Dr~ze and Richard (1983) - hereafter DR - express the following viewpoint about the present state of development of the Bayesian full information analysis of such sys- tems i) the method allows "e;a flexible specification of the prior density, including well defined noninformative prior measures"e;; ii) it yields "e;exact finite sample posterior and predictive densities"e;. However, they call for further developments so that these densities can be eval- uated through 'numerical methods, using an integrated software packa~e. To that end, they recommend the use of a Monte Carlo technique, since van Dijk and Kloek (1980) have demonstrated that "e;the integrations can be done and how they are done"e;. In this monograph, we explain how we contribute to achieve the developments suggested by Dr~ze and Richard. A basic idea is to use known properties of the porterior density of the param- eters of the structural form to design the importance functions, i. e. approximations of the posterior density, that are needed for organizing the integrations.