Lifetime Data

  • M. Luz Gámiz
  • K. B. Kulasekera
  • Nikolaos Limnios
  • Bo Henry Lindqvist
Part of the Springer Series in Reliability Engineering book series (RELIABILITY)


We study the smoothing of the classical Kaplan–Meier estimator for the survival function and the Nelson–Aalen estimator for the cumulative hazard function for a lifetime random variable discussing the practical and theoretical advantages of resulting estimators. We then extend our work to smoothing techniques such as kernel smoothing, local linear method, spline method, etc. for the estimation of failure rate functions in the presence of censoring. This is then followed by an introduction to smoothing parameter (bandwidth) selection. A few examples are presented to illustrate the use of some techniques.


Hazard Rate Kernel Estimator Empirical Distribution Function Hazard Rate Function Cumulative Hazard Function 
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.


  1. 1.
    Aalen O (1978) Non-parametric estimation of partial transition probabilities in multiple decrement models. Ann Stat 6:534–545MATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Anderson JA, Senthiselvan A (1980) Smooth estimates for the Hazard function. J R Stat Soc (B) 3:322–327Google Scholar
  3. 3.
    Breslow N (1972) Discussion on professor Cox’s paper, introduction to stochastic processes in biostatistics. Wiley, New YorkGoogle Scholar
  4. 4.
    Chen, SX (1999) Beta kernel estimators for density functions. Comput. Stati. Data. Anal 31:131-145 Google Scholar
  5. 5.
    Cox, DR and Oakes, D. (1984) Analysis of Survival Data. Chapman & Hall, London.MATHGoogle Scholar
  6. 6.
    Chen SX (2000) Probability density function estimation using gamma kernels. Ann Inst Stat Math 52:471–480MATHCrossRefGoogle Scholar
  7. 7.
    Efron B (1967) The two sample problem with censored data. Proc of the Fifth Berkeley Symp 4:831-853.Google Scholar
  8. 8.
    Eubank RL (1999) Nonparametric regression and spline smoothing. Marcel Dekker, New YorkMATHGoogle Scholar
  9. 9.
    Fleming TR, Harrington DP (1991) Counting processes and survival analysis. Wiley, NYMATHGoogle Scholar
  10. 10.
    Gasser T, Müller HG (1979) Kernel estimation of regression functions. Smoothing Techniques for Curve Estimation. Lecture Notes in Math 757:23–68Google Scholar
  11. 11.
    Ghorai JK, Susarla V (1990) Kernel estimation of a smooth distribution function based on censored data. Metrika 37:71–86MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Hess KR, Serachitopol BM, Brown DW (1999) Hazard functions estimators: a simulation study. Stat Med 18:3075–3088CrossRefGoogle Scholar
  13. 13.
    Jiang J, Doksum K (2003) On local polynomial estimation of hazard rates and their derivatives under random censoring, IMS Lecture Notes-Monograph Series, vol 42, Mathematical Statistics and Applications. pp 463–481Google Scholar
  14. 14.
    Kaplan EL, Meier P (1958) Nonparametric estimation from incomplete observations. J Am Stat Assoc 53:457–481MATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Karunamuni R, Yang S (1991) Weak and strong uniform consistency rates of kernel density estimates from randomly censored data. Can J Stat 19:349–359MATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Kooperberg C, Stone CJ, Young KT (1995) Hazard Regression, J. Am. Stat. Assoc. 90:78-94.MATHCrossRefGoogle Scholar
  17. 17.
    Kulasekera KB, Williams CL, Manatunga A (2001) Smooth estimation of the reliability function. Lifetime Data Anal 415–433Google Scholar
  18. 18.
    Kulasekera KB, Padgett WJ (2006) Bayes bandwidth selection in kernel density estimation from censored data. J Nonparametr Stat 18:129–143MATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Kuruwita CN, Kulasekera KB, Padgett WJ (2010) On boundary bias and bandwidth selection in density estimation with censored data, to appear in the J Stat Plan InferenceGoogle Scholar
  20. 20.
    Lawless JF (1998) Statistical models and methods for lifetime data. Wiley, NYGoogle Scholar
  21. 21.
    Lehmann LE, Cassella G (1998) Theory of point estimation. Springer, BerlinMATHGoogle Scholar
  22. 22.
    Marron JS, Padgett WJ (1987) Asymptotically optimal bandwidth selection for kernel density estimators from randomly right-censores samples. Ann Math Stat 15:1520–1535MATHMathSciNetGoogle Scholar
  23. 23.
    Marron JS, Wand MP (1992) Exact mean integrated squared error. Ann Stat 20:712–736MATHCrossRefMathSciNetGoogle Scholar
  24. 24.
    Müller HG, Wang JL (1994) Hazard rate estimation under random censoring with varying kernels and bandwidths. Biometrics 50:61–76.CrossRefGoogle Scholar
  25. 25.
    Müller HG, Wang JL (1990) Locally adaptive hazard smoothing. Prob Theory Related Fields 85:523–38MATHCrossRefGoogle Scholar
  26. 26.
    Nelson W (1984) Applied life data analysis. Wiley, NYGoogle Scholar
  27. 27.
    Parzen E (1962) On estimation of a probability density and mode. Ann Math Stat 35:1065–1076CrossRefMathSciNetGoogle Scholar
  28. 28.
    Patil PN (1993) On the least squares cross-validation bandwidth in hazard rate estimation. Ann Stat 21:1792–1810MATHCrossRefMathSciNetGoogle Scholar
  29. 29.
    Prakasa Rao BLS (1983) Nonparametric functional estimation. Academic Press, OrlandoMATHGoogle Scholar
  30. 30.
    Rice J, Rosenblatt M (1976) Estimation of the log survivor function and hazard function. Sankhya 38:60–78MATHMathSciNetGoogle Scholar
  31. 31.
    Reiss RD (1981) Nonparametric estimation of smooth distribution functions. Scand J Stat 8:116–119MATHMathSciNetGoogle Scholar
  32. 32.
    Scaillet O (2004) Density estimation using inverse and reciprocal inverse Gaussian kernels. J Nonparametr Stat 16:217–266MATHCrossRefMathSciNetGoogle Scholar
  33. 33.
    Singh RS (1977) Improvement on some known nonparametric uniformly consistent estimators of derivatives of a density. Ann Stat 5:394–399MATHCrossRefGoogle Scholar
  34. 34.
    Schucany WR, Sommers JP (1977) Improvement of kernel type density estimation. J Am Stat Assoc 72:420–423MATHCrossRefMathSciNetGoogle Scholar
  35. 35.
    Silverman B (1986) Density estimation for statistics and data analysis. Chapman and Hall, LondonMATHGoogle Scholar
  36. 36.
    Singpurwalla N, Wong WH (1983) Kernel estimators of the failure rate function and density estimation: an analogy. J Am Stat Assoc 78:478–481MATHCrossRefMathSciNetGoogle Scholar
  37. 37.
    Tanner M (1983) A note on the variable kernel estimator of the hazard function from randomly censored data. Ann Stat 11:994–998MATHCrossRefMathSciNetGoogle Scholar
  38. 38.
    Tanner M, Wong WH (1983) The estimation of the hazard function from randomly censored data by the kernel method. Ann Stat 11:989–993MATHCrossRefMathSciNetGoogle Scholar
  39. 39.
    Yandell B (1983) Nonparametric inference for rates with censored survival data. Ann Stat 11:1119–1135MATHMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  • M. Luz Gámiz
    • 1
  • K. B. Kulasekera
    • 2
  • Nikolaos Limnios
    • 3
  • Bo Henry Lindqvist
    • 4
  1. 1.Facultad Ciencias, Depto. Estadistica e Investigacion OperativaUniversidad GranadaGranadaSpain
  2. 2.Department of Mathematical SciencesClemson UniversityClemsonUSA
  3. 3.Centre de Recherches de Royallieu, Laboratoire de Mathématiques AppliquéesUniversité de Technologie de CompiègneCompiègneFrance
  4. 4.Department of Mathematical SciencesNorwegian University of Science and TechnologyTrondheimNorway

Personalised recommendations