Abstract
Quantifying safety goals is a key to the regulation of activities which are beneficial on the whole but entail some risks in being performed. Determining compliance with safety goals involves dealing with uncertainties. A recent article by BierI describes some of the difficulties encountered using measures with uncertainty to determine compliance with safety goals for nuclear reactors. This paper uses a hierarchical Bayes approach to address two practical modeling problems in determining safety goal compliance under uncertainty: (1) allowing some modeling assumptions to be relaxed, and (2) allowing data from previous related samples to be included in the analysis. The two issues effect each other to the extent that relaxing some assumptions allows the use of a broader range of data. The usefulness of these changes and their impact on assessing safety compliance for nuclear reactors is shown.
Original language | English (US) |
---|---|
Pages (from-to) | 229-237 |
Number of pages | 9 |
Journal | Risk Analysis |
Volume | 10 |
Issue number | 2 |
DOIs | |
State | Published - Jun 1990 |
Keywords
- Bayesian
- empirical Bayes
- hierarchical models
ASJC Scopus subject areas
- Safety, Risk, Reliability and Quality
- Physiology (medical)