Bayesian Full Information Analysis of the Simultaneous Equations Model

Abstract

Let observations be generated by the following system of structural equations:

$$ By\left( t \right)\; + \;\Gamma z\left( t \right) = u\left( t \right) $$

((1.1))

where y(t) is an m dimensional vector of endogenous variables, z(t) is an n-dimensional vector of truly exogenous variables, B is an m × m non-singular matrix of coefficients with diagonal elements B_ii = 1, i = 1,2,…,m, г is an m × n matrix of coefficients and u(t) is an m-dimensional vector of unobservable random disturbances with a non-degenerate joint distribution.¹