Bayes linear kinematics in the analysis of failure rates and failure time distributions (2010)

Author(s): Wilson KJ, Farrow M

    Abstract: Collections of related Poisson or binomial counts arise, for example, from numbers of failures insimilar machines or neighbouring time periods. A conventional Bayesian analysis requires a ratherindirect prior specification and intensive numerical methods for posterior evaluations.An alternative approach using Bayes linear kinematics in which simple conjugate specifications for individual counts are linked through a Bayes linear belief structure is presented. Intensive numerical methods are not required. The use of transformations of the binomial and Poisson parameters is proposed. The approach is illustrated in two examples, one involving a Poisson count of failures, the other involving a binomial count in an analysis of failuretimes.

      • Date: 01-12-2010
      • Journal: Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability
      • Volume: 224
      • Issue: 4
      • Pages: 309-321
      • Publisher: Sage Publications
      • Publication type: Article
      • Bibliographic status: Published

      Keywords: Bayesian inference, Bayes linear kinematics, count data, failure rates, failure times


      Dr Malcolm Farrow
      Senior Lecturer in Statistics

      Dr Kevin Wilson
      Lecturer in Statistics