On the estimation of a large sparse Bayesian system: The Snaer program

The Snaer program calculates the posterior mean and variance of variables on some of which we have data (with precisions), on some we have prior information (with precisions), and on some prior indicator ratios (with precisions) are available. The variables must satisfy a number of exact restrictions. The system is both large and sparse. Two aspects of the statistical and computational development are a practical procedure to solve a linear integer system, and a stable linearization routine for ratios. We test our numerical method to solve large sparse linear least-squares estimation problems, and find that it performs well, even when the n× k design matrix is large (nk ≈ 2). Corresponding author: Jan R. Magnus, CentER and Department of Econometrics & OR, Tilburg University, P.O. Box 90153, 5000 LE Tilburg, The Netherlands. Phone: +31-13-466-3092, fax: +31-13-466-3066, e-mail: [email protected].