Abstract
Nonhomogeneous Poisson process (NHPP) is a commonly used stochastic model that is utilized to describe the pattern of repeated occurrence of certain events or conditions. Aninhomogeneous gamma process evolves as a generalization to NHPP, where the observed failure epochs correspond to every successive κ-th event of the underlying Poisson process, κ being an unknown parameter to be estimated from the data. This article focuses on a special class of inhomogeneous gamma process, calledmodulated power law process (MPLP) that assumes the Weibull form of the intensity function. The traditional power law process is a popular stochastic formulation of certain empirical relationships between the time to failure and the cumulative number of failures, often observed in industrial experiments. The MPLP retains this underlying physical basis and provides a more flexible modeling environment potentially leading to a better fit to the failure data at hand. In this paper, we investigate inference issues related to MPLP. The maximum likelihood estimators (MLE’s) of the model parameters are not in closed form and enjoy the curious property that they are asymptotically normal with a singular variance-covariance matrix. Consequently, the derivation of the large-sample results requires non-standard modifications of the usual arguments. We also propose a set of simple closed-form estimators that are asymptotically equivalent to the MLE’s. Extensive simulation results are carried out to supplement the theoretical findings. Finally, we implement our inference results to a failure dataset arising from a repairable system.
Similar content being viewed by others
References
Abramowitz, M. and Stegun, I. A. (1974).Handbook of Mathematical Functions, with Formulas, Graphs, and Mathematical Tables, Dover Publications, New York.
Ascher, H. and Feingold, H. (1984),Repairable Systems Reliability: Modelling, Inference, Misconceptions and Their Causes, Marcel Dekker, New York.
Bain, L. J. and Engelhardt, M. (1980) Inferences on the parameters and current system reliability for a time truncated weibull process,Technometrics,22, 421–426.
Berman, M. (1981). Inhomogeneous and modulated gamma processes,Biometrika,68, 143–152.
Bhattacharyya, G. K. and Ghosh, J. K. (1991). Asymptotic properties of estimators in a binomial reliability growth model and its continuous-time analog,Journal of Statistical Planning and Inference,29, 43–53.
Black, S. E. and Rigdon, S. E. (1996). Statistical inference for a modulated power law process,Journal of Quality Technology,28, 81–90.
Chapman, D. G. (1956). Estimating the parameters of a truncated gamma distribution,Annals of Mathematical Statistics,27, 498–506.
Cox, D. R. (1967)Renewal Theory, Methuen, London.
Cox, D. R. (1972). The statistical analysis of dependencies in point processes,Stochastic Point Processes (ed. P. A. W. Lewis), 55–66, Wiley, New York.
Cox, D. R. and Isham, V. (1980).Point Process Chapman and Hall, London.
Cox, D. R. and Lewis, P. A. W. (1966)The Statistical Analysis of Series of Events, Methuen, London.
Crow, L. R. (1974). Reliability analysis for complex repairable systems,Reliability and Biometry (eds. F. Proschan and R. J. Serfling), 379–410, SIAM, Philadelphia.
Crow, L. R. (1982). Confidence interval procedures for the weibull process with applications to reliability growth,Technometrics,24, 67–72.
Duane, J. T. (1964). Learning curve approach to reliability monitoring,IEEE Transactions on Aerospace,2, 563–566.
Hager, H. W. and Bain, L. J. (1970). Inferential procedures for the generalized gamma distribution,Journal of the American Statistical Association,65, 1601–1609.
Harter, H. L. (1967). Maximum-likelihood estimation of the parameters of a four-parameter generalized gamma population from complete and censored samples,Technometries,9, 159–165.
Lakey, M. J. and Rigdon, S. E. (1992). The modulated power law process,Proceedings of the 45th Annual Quality Congress, 559–563, Milwaukee, Wisconsin.
Lawless, J. F. (1980). Interence in the generalized gamma and long gamma distributions,Technometrics,22, 409–419.
Lawless, J. F. and Thiagarajah, K. (1996). A point-process model incorporating renewals and time trends, with application to repairable systems,Technometrics,38, 131–138.
Lawless, J. F., Wigg, M. B., Tuli, S., Drake, J. M. and Lamberti-Pasculli, M. (2001). Analysis of repeated failures or durations, with application to shunt failures for patients with pediatric hydrocephalus,Applied Statistics,50, 449–465.
Masuyama, M. and Kuroiwa, Y. (1952). Table for the likelihood solutions of gamma distribution and its medical application,Reports of Statistical Application Research (JUSE),1, 18–23.
MIL-HDBK-781 (1997).Handbook for Reliability Test Methods Plans, and Environments for Engineering, Development Qualification, and Production, United States Government Printing Office, Washington.
Parr, V. B. and Webster, J. T. (1965). A method for discriminating between failure density functions used in reliability predictions,Technometrics,7, 1–10.
Prentice, R. L. (1974). A log-gamma model and its maximum likelihood estimation,Biometrika,61, 539–544.
Rigdon, S. E. and Basu, A. P. (1989). The power law process: A model for the reliability of repairable systems,Journal of Quality Technology,20, 251–260.
Sen, A. and Bhattacharyya, G. K. (1993). A piecewise exponential model for reliability growth and associated inferences,Advances in Reliability (ed. A. P. Basu), 331–355, Elsevier, Amsterdam.
Sen, A. and Fries, A. (1997). Estimation in a discrete reliability growth model under an inverse sampling scheme,Annals of the Institute of Statistical Mathematics,49, 211–229.
Stacey, E. W. and Mihram, G. A. (1965). Parameter estimation for a generalized gamma distribution,Technometrics,7, 349–358.
Author information
Authors and Affiliations
About this article
Cite this article
Bandyopadhyay, N., Sen, A. Non-standard asymptotics in an inhomogeneous gamma process. Ann Inst Stat Math 57, 703–732 (2005). https://doi.org/10.1007/BF02915434
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02915434