Zellner 9629834 the investigator and colleagues organize a workshop on Markov chain Monte Carlo (MCMC) techniques. These techniques, originally developed in mathematics and physics, have come to be of great importance in many sciences and fields of application. Their use allows researchers and applied workers to solve many theoretical and applied problems. While MCMC techniques have already been shown to be of great value, more work has to be done to improve them. For example, new methods are being developed to speed convergence of MCMC techniques, to check on the convergence and accuracy of MCMC output, and to provide computer systems and programs needed to implement MCMC techniques in a user-friendly, interactive environment. These are a subset of the topics, including new applications, that are discussed at the workshop. the investigator and colleagues organize a workshop on Markov chain Monte Carlo (MCMC) techniques. Monte Carlo techniques are ways to make probabilistic estimates of quantities. For example, the volumes of a complicated shape can be estimated by making random samples of the shape when embedded in a simpler shape. MCMC techniques have already been of great value in solving important problems in science, industry and government. In this connection, models are employed to explain past behavior, predict future outcomes and evaluate proposed policies. Deriving good solutions involves needed calculations that are best carried out by use of MCMC techniques in many instances, e.g. in connection with the analysis of global warming, financial asset-pricing, industry personnel decisions, on-line quality control and governmental policy problems. Better MCMC techniques, and more informed users of them, contribute to better solutions to these and other private and public scientific and policy problems.
