Calibration in a Bayesian modelling framework

Authors

  • M.J.W. Jansen
  • T.J. Hagenaars

Abstract

Bayesian statistics may constitute the core of a consistent and comprehensive framework for the statistical aspects of modelling complex processes that involve many parameters whose values are derived from many sources. Bayesian statistics holds great promises for model calibration, provides the perfect starting point for uncertainty analysis and provides an excellent starting point for decision support. The purpose of this paper is to draw attention to problems and possible solutions. It is not our intention to introduce ready-for-use methods

Downloads

Published

2004-05-01