Premium
Comparing conditional probabilities and statistical independence in layers of protection analysis
Author(s) -
Mott Timothy C.,
Kivistik Paul Michael,
Panorska Anna K.,
Cantu David C.
Publication year - 2021
Publication title -
process safety progress
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.378
H-Index - 40
eISSN - 1547-5913
pISSN - 1066-8527
DOI - 10.1002/prs.12215
Subject(s) - conditional independence , independence (probability theory) , conditional probability , law of total probability , event (particle physics) , statistics , econometrics , conditional expectation , mathematics , posterior probability , bayesian probability , physics , quantum mechanics
Abstract This paper demonstrates an approach to include conditional probabilities when calculating probabilities of disaster in quantitative risk analysis. Since not all layers of protection are independent of each other, using conditional probabilities leads to more accurate calculations of probabilities of disaster in a chemical process. An event tree analysis approach is shown by calculating probabilities of disaster assuming that events are statistically independent (independence assumption), and separately considering that events affect each other (conditional probabilities), in three cases with increasing complexity and number of layers of protection. For each case, we considered multiple scenarios to show that results do not depend on the input probabilities of particular events. In most scenarios of the three cases, findings demonstrate that the probabilities of disaster calculated using the independence assumption are lower than those with conditional probabilities, which can lead to undercounting the layers of protection that are actually needed.