Abstract

Several examples of probabilistic models often used to analyze fault trees, common mode failures, and decision trees are discussed to show that each is a special case of a general model. The general model is PAR (Probabilistic Analysis of Risks), and its use enhances the understanding and interpretation of this type of analysis. Experience with this method of analysis over the past few years has shown that the generality originally incorporated in the method may have obscured its real usefulness. Many types of real life situations (fault trees, event trees, decision trees, and common mode failures) are special cases of the PAR method. The numerical answer that results from the analysis of any one of these special cases is not likely to be as accurate as a single number implies. The content and extent of the analysis are more important than the single numerical answer. A broad range of meaning, significance, and implications can be reviewed by examining these problems through the generality of the PAR method. The PAR method was intentionally designed to provide a flexibility that would assist in easing the task of assembling and reviewing the input data, especially in those cases where the data must reflectmore » primarily judgment factors. Greater generality will hopefully prevent the false sense of security provided by a single numerical answer and a restricted view of the problem.« less

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call