Lifetime Data Analysis

, Volume 10, Issue 3, pp 213–227 | Cite as

Covariates and Random Effects in a Gamma Process Model with Application to Degradation and Failure

  • Jerry Lawless
  • Martin Crowder


The gamma process is a natural model for degradation processes in which deterioration is supposed to take place gradually over time in a sequence of tiny increments. When units or individuals are observed over time it is often apparent that they degrade at different rates, even though no differences in treatment or environment are present. Thus, in applying gamma-process models to such data, it is necessary to allow for such unexplained differences. In the present paper this is accomplished by constructing a tractable gamma-process model incorporating a random effect. The model is fitted to some data on crack growth and corresponding goodness-of-fit tests are carried out. Prediction calculations for failure times defined in terms of degradation level passages are developed and illustrated.

degradation frailty gamma process random effects reliability repeated measures wear 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. O. Aalen and H. K. Gjessing,#x201C;Understanding the shape of the hazard rate: a process point of view (with discussion)#x201D;, Statistical Science vol. 16 pp. 1–22, 2001.Google Scholar
  2. M. Abramowitz and I. A. Stegun, Handbook of Mathematical Functions, Dover: New York, 1965.Google Scholar
  3. P. K. Andersen, O. Borgan, R. D. Gill and N. Keiding, Statistical Models Based on Counting Processes, Springer-Verlag: New York, 2001.Google Scholar
  4. V. Bagdonavicius and M. Nikulin,#x201C;Estimation in degradation models with explanatory variables,#x201D; Lifetime Data Analysis vol. 7 pp. 85–103, 2001.Google Scholar
  5. E. Cinlar,#x201C;On a generalization of gamma processes,#x201D; Journal of Applied Probability vol. 17 pp. 467–480, 1980.Google Scholar
  6. M. J. Crowder and D. J. Hand, Analysis of Repeated Measures, Chapman and Hall: London, 1990.Google Scholar
  7. A. C. Davison and D. V. Hinkley, Bootstrap Methods and Their Application, Cambridge University Press, Cambridge: U.K., 1997.Google Scholar
  8. K. A. Doksum, and A. Hoyland,#x201C;Models for variable-stress accelerated life test experiments based on Wiener processes and the inverse Gaussian distribution,#x201D; Technometrics vol. 34 pp. 74–82, 1992.Google Scholar
  9. R. L. Dykstra and P. Laud,#x201C;A Bayesian nonparametric approach to reliability,#x201D; Annals of Statistics vol. 9 pp. 356–367, 1981.Google Scholar
  10. T. S. Ferguson and M. J. Klass,#x201C;A representation of independent increments processes without Gaussian components,#x201D; Annals of Mathematical Statistics vol. 43 pp. 1634–1643, 1972.Google Scholar
  11. S. J. Hudak, A. Saxena, R. J. Bucci, and R. C. Malcolm,#x201C;Development of standard methods of testing and analyzing fatigue crack growth rate data,#x201D; Technical Report AFML-TR-78-40, Westinghouse R & D Center, Westinghouse Electric Corporation, Pittsburgh, PA, 1978.Google Scholar
  12. J. D. Kalbfleisch,#x201C;Bayesian nonparametric analysis of survival data,#x201D; Journal of the Royal Statistical Society B vol. 40 pp. 214–221, 1978.Google Scholar
  13. C. J. Lu and W. Q. Meeker#x201C;Using degradation measurements to estimate a time-to-failure distribution,#x201D; Technometrics vol. 35 pp. 161–174, 1993.Google Scholar
  14. W. Q. Meeker and L. E. Escobar, Statistical Methods for Reliability Data, John Wiley and Sons: New York, 1998.Google Scholar
  15. P. A. P. Moran, The Theory of Storage, Methuen: London, 1959.Google Scholar
  16. M. E. Robinson and M. J. Crowder#x201C;Bayesian methods for a growth-curve degradation model with repeated measures,#x201D; Lifetime Data Analysis vol. 6 pp. 357–374, 2000.Google Scholar
  17. N. D. Singpurwalla,#x201C;Survival in dynamic environments,#x201D; Statistical Science vol. 1 pp. 86–103, 1995.Google Scholar
  18. D. A. Virkler, B. M. Hilberry, and P. K. Goel#x201C;The statistical nature of fatigue crack propagation,#x201D; Trans. ASME pp. 148–153, 1979.Google Scholar
  19. G. A. Whitmore,#x201C;Normal-gamma mixtures of inverse Gaussian distributions,#x201D; Scandanavian Journal of Statistics vol. 13 pp. 211–220, 1986.Google Scholar
  20. G. A. Whitmore,#x201C;Estimating degradation by a Wiener diffusion process,#x201D; Lifetime Data Analysis vol. 1 pp. 307–319, 1995.Google Scholar
  21. G. A. Whitmore and F. Schenkelberg,#x201C;Modelling accelerated degradation data using Wiener diffusion with a time scale transformation,#x201D; Lifetime Data Analysis vol. 3 pp. 27–45, 1997.Google Scholar

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Jerry Lawless
    • 1
  • Martin Crowder
    • 2
  1. 1.Department of Statistics and Actuarial ScienceUniversity of WaterlooWaterlooCanada
  2. 2.Department of MathematicsImperial CollegeLondonUK

Personalised recommendations