Bayesian Failure Probability Model Sensitivity Study.
Abstract
The Office of the Manager, National Communications System (OMNCS) has developed a system-level approach for estimating the effects of High-Altitude Electromagnetic Pulse (HEMP) on the connectivity of telecommunications networks. This approach incorporates a Bayesian statistical model which estimates the HEMP-induced failure probabilities of telecommunications switches and transmission facilities. the purpose of this analysis is to address the sensitivity of the Bayesian model. This is done by systematically varying two model input parameters--the number of observations, and the equipment failure rates. Throughout the study, a non-informative prior distribution is used. The sensitivity of the Bayesian model to the non-informative prior distribution is investigated from a theoretical mathematical perspective. Keywords: probability density functions; cumulative distribution functions; statistical models.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 30, 1986
- Accession Number
- ADA183877
Entities
Organizations
- Booz Allen Hamilton