Advertisement

Probability Theory and Related Fields

, Volume 80, Issue 3, pp 461–473 | Cite as

Density and hazard rate estimation for censored data via strong representation of the Kaplan-Meier estimator

  • S. H. Lo
  • Y. P. Mack
  • J. L. Wang
Article

Summary

We study the estimation of a density and a hazard rate function based on censored data by the kernel smoothing method. Our technique is facilitated by a recent result of Lo and Singh (1986) which establishes a strong uniform approximation of the Kaplan-Meier estimator by an average of independent random variables. (Note that the approximation is carried out on the original probability space, which should be distinguished from the Hungarian embedding approach.) Pointwise strong consistency and a law of iterated logarithm are derived, as well as the mean squared error expression and asymptotic normality, which is obtain using a more traditional method, as compared with the Hajek projection employed by Tanner and Wong (1983).

Keywords

Mathematical Biology Hazard Rate Rate Estimation Independent Random Variable Asymptotic Normality 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barlow, R.E., Proschan, F.: Statistical theory of reliability and life testing: probability models. Holt, Rinehart and Winston, New York 1975Google Scholar
  2. 2.
    Blum, J.R., Susarla, V.: Maximal deviation theory of density and failure rate function estimates based on censored data. In: Krishnaiah, P.R. (ed.) Mult. Analysis vol. V, pp. 213–222 New York: North Holland, 1980Google Scholar
  3. 3.
    Breslow, N., Crowley, J.: A large sample study of the life table and product-limit estimates under random censorship. Ann. Stat.2, 437–443 (1974)Google Scholar
  4. 4.
    Burke, M.D.: Approximations of some hazard rate estimators in a competing risks model. Stoch. Processes Appl.14, 157–174 (1983)Google Scholar
  5. 5.
    Burke, M.D., Csörgő, S., Horváth, L.: A correction to and an improvement of strong approximation of some biometric estimates under random censorship. Probab. Th. Rel. Fields79, 51–57 (1988)Google Scholar
  6. 6.
    Burke, M.D., Horváth, L.: Density and failure rate estimation in a competing risks model. Sankhyā Ser. A.46, 135–154 (1984)Google Scholar
  7. 7.
    Földes, A., Rejtö, L., Winter, B.B.: Strong consistency properties of nonparametric estimators for randomly censored data. II: Estimation of density and failure rate. Period. Math. Hung.12, 15–29 (1981)Google Scholar
  8. 8.
    Hajek, J.: Asymptotic normality of simple linear statistics under alternatives. Ann. Math. Stat.39, 325–346 (1968)Google Scholar
  9. 9.
    Hall, P.: Laws of the iterated logarithm for nonparametric density estimators. Z. Wahrscheinlichkeitstheor. Verw. Geb.56, 47–61 (1981)Google Scholar
  10. 10.
    Kaplan, E.L., Meier, P.: Nonparametric estimation from incomplete observations. J. Am. Stat. Assoc.53, 457–481 (1958)Google Scholar
  11. 11.
    Liu, R.Y.C., Van Ryzin, J.: A histogram estimator of the hazard rate with censored data. Ann. Stat.13, 592–605 (1985)Google Scholar
  12. 12.
    Lo, S.H., Mack, Y.P., Wang, J.L.: Density and hazard rate estimation for censored data via strong representation of the Kaplan-Meier estimator. Tech. Rep. No. 64, University of California, Davis. (1985)Google Scholar
  13. 13.
    Lo, S.-H., Singh, K.: The product-limit estimator and the bootstrap: Some asymptotic representations. Probab. Th. Rel. Fields71, 455–465 (1986)Google Scholar
  14. 14.
    Mack, Y.P., Rosenblatt, M.: Multivariatek-nearest neighbor density estimates. J. Multivariate. Anal.9, 1–15 (1979)Google Scholar
  15. 15.
    Mileniczuk, J.: Some asymptotic properties of kernel estimators of a density function in case of censored data. Ann. Stat.13, 766–773 (1986)Google Scholar
  16. 16.
    Padgett, W.J., McNichols, D.T.: Nonparametric density estimation from censored data. Commun. Stat. Theory Methods13, 1581–1613 (1984)Google Scholar
  17. 17.
    Ramlau-Hansen, H.: Smoothing counting process intensities by means of kernel functions. Ann. Stat.11, 453–466 (1983)Google Scholar
  18. 18.
    Rice, J., Rosenblatt, M.: Estimation of the log survivor function and hazard function. Sankhya Ser. A38, 60–78 (1976)Google Scholar
  19. 19.
    Singpurwalla, N.D., Wong, M.-Y.: Kernel estimators of the failure rate function and density function: An analogy. J. Am. Stat. Assoc.78, 478–481 (1983)Google Scholar
  20. 20.
    Tanner, M.A.: A note of the variable kernel estimator of the hazard function from randomly censored data. Ann. Stat.11, 994–998 (1983)Google Scholar
  21. 21.
    Tanner, M.A., Wong, W.H.: The estimation of the hazard function from randomly censored data by the kernel method. Ann. Stat.11, 989–993 (1983)Google Scholar
  22. 22.
    Walter, G., Blum, J.R.: Probability density estimation using delta sequences. Ann. Stat.7, 328–340 (1979)Google Scholar
  23. 23.
    Watson, G.S., Leadbetter, M.R.: Hazard analysis. I. Biometrika51, 175–184 (1964a)Google Scholar
  24. 24.
    Watson, G.S., Leadbetter, M.R.: Hazard analysis. II. Sankhyā Ser. A26, 101–116 (1964 b)Google Scholar
  25. 25.
    Yandell, B.S.: Nonparametric inference for rates and densities with censored serial data. Ph.D. dissertation, Biostatistics Program, University of California, Berkeley (1981)Google Scholar
  26. 26.
    Yandell, B.S.: Nonparametric inference for rates and densities with censored survival data. Ann. Stat.11, 1119–1135 (1983)Google Scholar

Copyright information

© Springer-Verlag 1989

Authors and Affiliations

  • S. H. Lo
    • 1
  • Y. P. Mack
    • 2
  • J. L. Wang
    • 2
  1. 1.Department of StatisticsHarvard UniversityCambridgeUSA
  2. 2.Division of StatisticsUniversity of CaliforniaDavisUSA

Personalised recommendations