Likelihood Testing With Censored and Missing Duration Data
Duration data of a component, product, or system are often incomplete. We give guidelines for likelihood ratio testing for small samples with some data imperfections, that is, when some information is missing and some information is censored. We introduce the model of the missing time-to-failure mechanism, which still enables the exact likelihood ratio testing of the scale and homogeneity. Such a model encompasses well both the generalized gamma and Pareto duration time models with missing individual times to failure. The exact distribution of the likelihood ratio test for the censored sample from Weibull distribution with known shape parameter is derived and discussed. We discuss separately Type I, Type II, and progressively censored samples. We show that the Type I censoring and Type II censoring differ substantially. The construction of the pivotal quantity is possible for Type II and progressively Type II censoring; however, it is not available for the case of Type I censoring. Thus, for the latter case the usage of the exact likelihood ratio test is a natural option. We also discuss the case of the generalized gamma distribution. For the case with nuisance shape parameters we use an integrated likelihood approach. Convenient examples illustrate the methods developed in the article.
KeywordsExact test Integrated likelihood Lambert W function Likelihood ratio Missing data Nuisance parameter Profile likelihood Progressive censoring Type I censoring Type II censoring
AMS Subject Classification62E15
Unable to display preview. Download preview PDF.
- Amstadter, B. L. 1971. Reliability mathematics, chap. 9. New York, NY: McGraw-Hill.Google Scholar
- Bahadur, R. R. 1965. An optimal property of the likelihood ratio statistic. In Proc. 5th Berkeley Symposium on Probability Theory and Mathematical Statistics, vol. 1, ed. L. Le Cam and J. Neyman, 13–26. Berkeley, CA: University of California Press.Google Scholar
- Bain, L. J., and M. Engelhardt. 1992. Introduction to probability and mathematical statistics (2nd ed.). Boston, MA: PWSKENT Publishing Company.Google Scholar
- Barndorf-Nielsen, O. E. 1978. Information and exponential families in statistical theory, 111–115. New York, NY: John Wiley Sons.Google Scholar
- Coit, D. W., and T. Jin. 2000. Gamma distribution parameter estimation for field reliability data with missing failure times. IIE Trans. 32, 1161–1166.Google Scholar
- Corless, R. M., G. H. Gonnet, D. E. G. Hare, D. J. Jeffrey and D. E. Knuth. 1993. Lambert’s W function in Maple. Maple Tech. Newslett., 9, 12–22.Google Scholar
- Dey, K. A. 1982. Statistical analysis of noisy and incomplete failure data. In Proceedings Annual Reliability and Maintainability Symposium (RAMS), IEEE, Piscataway, NJ, 93–97.Google Scholar
- Economou, P., and M. Stehlík. 2014. On small samples testing for frailty through homogeneity test. Commun. Stat. Simul. Comput. http://dx.doi.org/10.1080/03610918.2013.763982.
- Gautam, N. 1999. Erlang distribution: Description and case study. In Industrial engineering applications and practice: Users encyclopedia, eds. A. Mitaland J. Chen.Google Scholar
- Johansen, S. 1979. Introduction to the theory of regular exponential families. Lecture Notes, vol. 3. Copenhagen, Denmark: Institute of Mathematical Statistics, University of Copenhagen.Google Scholar
- Philbrick, S. W. 1985. A practical guide to the single parameter Pareto distribution. Proc. Casualty Actuarial Society, LXXII, 44–84.Google Scholar
- Soland, R. M. 1966. Use of Weibull distribution in Bayesian decision theory, Report No. RAC-TP-225. McLean, VA: Research Analysis Corporation.Google Scholar
- Stehlík, M. 2007. Exact testing of the scale with the missing time-to-failure information. Commun. Dependability Qual. Manage. Eng. (CDQM), 10(2), 124–129.Google Scholar