Properties of Residual Mixing Distributions Resulting from Arbitrary Mixtures of Exponential Life Distributions.

Abstract

A mixture of failure rates can be present in an apparently homogeneous population of devices due to variability either in their manufacture or in the severity of their service environments. An initial mixing distribution is the probability distribution for different failure rates in such a population. This distribution may be updated to yield its related residual mixing distribution, which is the probability distribution for different failure rates in the population of survivors after a specified period of service or burn-in. Residual mixing distributions resulting from arbitrary mixtures of constant failure rates are shown to be stochastically ordered (decreasingly) as the period of service or burn-in is increased, and to approach in the limit a distribution degenerate at the smallest failure rate present in the population. Properties of expected value ordering, stochastic ordering, failure rate ordering and likelihood ratio ordering are investigated to show that, of these, only likelihood ratio ordering between two initial mixing distributions is sufficient to guarantee an ordering between the expected values of their respective residual mixing distributions over time. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1977
Accession Number
ADA042174

Entities

People

  • David Russell Campbell

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Ground and Sea Platforms

DTIC Thesaurus Topics

  • Fleet Ballistic Missiles
  • Guarantees
  • Integrals
  • Mathematics
  • New York
  • Operations Research
  • Probabilistic Models
  • Probability
  • Probability Distributions
  • Random Variables
  • Reliability
  • Residuals
  • Sequences
  • United States
  • Universities

Fields of Study

  • Mathematics

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Fluid Dynamics.
  • Materials Science and Engineering.