DID YOU KNOW? DTIC has over 3.5 million final reports on DoD funded research, development, test, and evaluation activities available to our registered users. Click HERE
to register or log in.
Bayesian Failure Probability Model Sensitivity Study.
BOOZ-ALLEN AND HAMILTON INC BETHESDA MD
Pagination or Media Count:
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.
APPROVED FOR PUBLIC RELEASE