Algorithms for Bayesian Computing and Mathematica
One approach to developing a general-purpose Bayesian computing system is to add a package of Bayesian commands to a mathematics/statistics program. Due to its symbolic algebra system, the program Mathematica appears very suitable for the implementation of the Laplace method. The use of a Laplace Bayesian package is illustrated.
KeywordsPosterior Distribution Marginal Density Laplace Approximation Monte Carlo Integration Mathematica Package
Unable to display preview. Download preview PDF.
- Albert, J. H. (1990), “LapApprox.m: A Mathematica Package to apply the Laplace method in a Bayesian Analysis”, Technical report, Department of Mathematics and Statistics, Bowling Green State University.Google Scholar
- Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988), The New-S Language, Wadsworth.Google Scholar
- Geweke, J. (1990), “Generic, algorithmic approaches to Monte Carlo integration in Bayesian inference”, to appear in Contemporary Mathematics.Google Scholar
- Goel, P. K. (1988), “Software for Bayesian analysis: current status and additional needs — II”, Technical report, Department of Statistics, Ohio State University.Google Scholar
- Naylor, J. and Shaw, J. E. H. (1985), “Bayes 4 — User Guide”, Technical report, Department of Mathematics, University of Nottingham.Google Scholar
- Tierney, L. (1988), “XLISP-STAT: A statistical environment based on the XLISP language,” Technical report, School of Statistics, University of Minnesota.Google Scholar
- Wolfram, S. (1988), Mathematica: A System for Doing Mathematics by Computer, Addison Wesley.Google Scholar