Predicting incident size from limited information

Research output: Chapter in Book/Report/Conference proceedingChapter

25 Scopus citations


Predicting the size of low-probability, high-consequence natural disasters, industrial accidents, and pollutant releases is often difficult due to limitations in the availability of data on rare events and future circumstances. Two Bayesian probability distributions for inferring future incident-size probabilities from limited, indirect, and subjective information are proposed in this paper. The distributions are derived from Pareto distributions that are shown to fit data on different incident types and are justified theoretically. Use of the distributions to predict accumulated oil-spill consequences was demonstrated. -from Author

Original languageEnglish
Title of host publicationJournal of Environmental Engineering - ASCE
Number of pages10
StatePublished - Jan 1 1995

ASJC Scopus subject areas

  • Environmental Science(all)
  • Earth and Planetary Sciences(all)
  • Engineering(all)
  • Civil and Structural Engineering
  • Environmental Chemistry
  • Environmental Engineering


Dive into the research topics of 'Predicting incident size from limited information'. Together they form a unique fingerprint.

Cite this