• DocumentCode
    1111474
  • Title

    Tests of univariate and bivariate stochastic ageing

  • Author

    Lai, C.D.

  • Author_Institution
    Massey Univ., Palmerston North, New Zealand
  • Volume
    43
  • Issue
    2
  • fYear
    1994
  • fDate
    6/1/1994 12:00:00 AM
  • Firstpage
    233
  • Lastpage
    241
  • Abstract
    Concepts of ageing describe how a population of units or systems improves or deteriorates with age. Many classes of life distributions are categorized and defined in the literature according to their ageing properties. An important aspect of such classifications is that the exponential distribution is nearly always a member of each class. The notion of stochastic ageing is important in any reliability analysis, and many test statistics have been developed for testing exponentiality against various ageing alternatives. This paper is an overview of these developments. The author begins with a table of ageing classes together with key references, followed by a brief discussion on the characterization of exponentiality. Test procedures are summarized, and followed by the main review. Tests of exponentiality against other alternatives are explained for randomly censored data. Finally, tests of multivariate ageing properties are listed. Some of the life classes have been derived more recently and, as far as is known, no test statistics have been proposed. On the other hand, several tests are available for some classes. Relative efficiency of a test is discussed whenever appropriate
  • Keywords
    ageing; reliability theory; statistical analysis; stochastic processes; ageing classes; asymptotic normality; bivariate stochastic ageing; exponential distribution; exponentiality characterisation; hypothesis test; increasing failure rate; life distributions; randomly censored data; relative test efficiency; reliability analysis; residual life; stochastic ageing tests; test statistics; univariate stochastic ageing; Aging; Exponential distribution; Hazards; Laplace equations; Life testing; Performance evaluation; Stochastic processes;
  • fLanguage
    English
  • Journal_Title
    Reliability, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0018-9529
  • Type

    jour

  • DOI
    10.1109/24.294999
  • Filename
    294999