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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 30, 1986
Accession Number
ADA183877

Entities

Organizations

  • Booz Allen Hamilton

Tags

DTIC Thesaurus Topics

  • Altitude
  • Bayesian Inference
  • Bayesian Networks
  • Classification
  • Communication Systems
  • Distribution Functions
  • Electromagnetic Pulses
  • High Altitude
  • Models
  • National Security
  • Normal Distribution
  • Observation
  • Probability
  • Probability Density Functions
  • Probability Distributions
  • Security
  • Standards

Readers

  • Computational Modeling and Simulation
  • Optical Fiber Sensing and Electromagnetic Propagation.
  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference