Top-down versus bottom-up processing of influence diagrams in probabilistic analysis
Recent work by Phillips et al., and Selby et al., has shown that influence diagram methodology can be a useful analytical tool in reactor safety studies. An influence diagram is a graphical representation of probabilistic dependence within a system or event sequence. Bayesian statistics are employed to transform the relationships depicted in the influence diagram into the correct expression for a desired marginal probability (e.g. the top event). As with fault trees, top-down and bottom-up algorithms have emerged as the dominant methods for quantifying influence diagrams. Purpose of this paper is to demonstrate a potential error in employing the bottom-up algorithm when dealing with interdependencies. In addition, the computing efficiency of both methods is discussed.
- Research Organization:
- Tennessee Univ., Knoxville (USA); Oak Ridge National Lab., TN (USA)
- DOE Contract Number:
- AC05-84OR21400
- OSTI ID:
- 6079284
- Report Number(s):
- CONF-841105-53; ON: DE85005381
- Resource Relation:
- Conference: Joint meeting of the American Nuclear Society and the Atomic Industrial Forum, Washington, DC, USA, 11 Nov 1984
- Country of Publication:
- United States
- Language:
- English
Similar Records
Top-down versus bottom-up processing of influence diagrams in probabilistic analysis
Top-down and bottom-up definitions of human failure events in human reliability analysis