RISK ANALYSIS AND SCIENCE

Abstract

In this paper we discuss the scientific basis of risk analysis, when a Bayesian approach is the foundation of the analysis. We argue that the analysis cannot be judged by reference to the traditional science paradigms alone, such as the natural sciences, social sciences, mathematics and probability theory. There is a need for recognitions of a risk analysis science which is related to the establishment of principles, methods and models to analysis, describe and communicate risk, in a decision-making context. The "goodness" of these principles, methods and models cannot be evaluated by reference to the accuracy in describing the world, as risk analysis is a tool for expressing and communicating uncertainty about the world. Empirical control is only relevant to some degree. An example of a risk analysis of an offshore installation is used to illustrate important issues.