|
Activity Number:
|
244
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 8, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Risk Analysis
|
| Abstract - #307425 |
|
Title:
|
A Comparison of Bayesian Networks and MCMC Techniques for Quantitative Risk Assessment
|
|
Author(s):
|
Paola Berchialla*+ and Silvia Snidero and Alexandru Stancu and Cecilia Scarinzi and Roberto Corradetti and Dario Gregori
|
|
Companies:
|
University of Torino and University of Torino and University of Torino and University of Torino and University of Torino and University of Torino
|
|
Address:
|
Department of Statistics, Torino, 10122, Italy
|
|
Keywords:
|
Bayesian networks ; Markov chain Monte Carlo ; quantitative risk assessment
|
|
Abstract:
|
Bayesian Networks (BNs) have been successfully applied to a great number of classification problems and have been used to develop quantitative risk assessment models. The BN responds immediately to changes, such as entering evidence, because it does not use simulation and can propagate information from any point in the network to all others by Bayes's theorem. However conventional Bayesian networks require discretization of continuous prior to learning which introduces errors if continuous variables have to be discretized. Markov chain Monte Carlo approach does not require discrete variables while retaining some of the properties of the BN model, such as the ability to draw inferences from evidence. A comparison of these modeling approaches for a quantitative risk assessment model is proposed using the case study of foreign body injuries in children.
|
