Advertisement

Semiparametric Estimation Of Parametric Hazard Rates

  • Nils Lid Hjort
  • Mike West
  • Sue Leurgans
Chapter
Part of the Nato Science book series (NSSE, volume 211)

Abstract

The best known methods for estimating hazard rate functions in survival analysis models are either purely parametric or purely nonparametric. The parametric ones are sometimes too biased while the nonparametric ones are sometimes too variable. There should therefore be scope for methods that somehow try to combine parametric and nonparametric features. In the present paper three semiparametric approaches to hazard rate estimation are presented. The first idea uses a dynamic local likelihood approach to fit the locally most suitable member in a given parametric class of hazard rates. Thus the parametric hazard rate estimate at time s inserts a parameter estimate that also depends on s. The second idea is to write the true hazard as a product of an initial parametric estimate times a correction factor, and then estimate this factor nonparametrically using orthogonal expansions. Finally the third idea is Bayesian in flavour and builds a larger nonparametric hazard process prior around a given parametric hazard model. The hazard estimate in this case is the posterior expectation. Properties of the resulting estimators are discussed.

Keywords

Hazard Rate Gibbs Sampling Dirichlet Process Cumulative Hazard Orthogonal Expansion 
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. Abramowitz, M. and Stegun, I. A. (1964). Handbook of Mathematical Functions. National Bureau of Standards, Washington.zbMATHGoogle Scholar
  2. Andersen, P. K. and Borgan, Ø. (1985). Counting process models for life history data: A review (with discussion). Scandinavian Journal of Statistics 12, 97–158.MathSciNetzbMATHGoogle Scholar
  3. Andersen, P. K., Borgan, Ø., Gill, R. D., and Keiding, N. L. (1991). Statistical Models Based on Counting Processes. Springer Verlag, to appear.Google Scholar
  4. Borgan, Ø. (1984). Maximum likelihood estimation in parametric counting process models, with applications to censored failure time data. Scandinavian Journal of Statistics 11, 1–16. Corrigendum, ibid. 275.MathSciNetzbMATHGoogle Scholar
  5. Gill, R. D. and Johansen, S. (1990). A survey of product-integration with a view toward application in survival analysis. Annals of Statistics 18, 1501–1555.MathSciNetzbMATHCrossRefGoogle Scholar
  6. Hjort, N. L. (1985a). Contribution to the discussion of Andersen and Borgan’s “Counting process models for life history data: a review”. Scandinavian Journal of Statistics 12, 141–150.Google Scholar
  7. Hjort, N. L. (1985b). Bootstrapping Cox’s regression model. Technical Report NSF—241, Department of Statistics, Stanford University.Google Scholar
  8. Hjort, N. L. (1986a). Bayes estimators and asymptotic efficiency in parametric counting process models. Scandinavian Journal of Statistics 13, 63–85.MathSciNetzbMATHGoogle Scholar
  9. Hjort, N. L. (1986b). Statistical Symbol Recognition. Research Monograph, Norwegian Computing Centre, Oslo.Google Scholar
  10. Hjort, N. L. (1986c). Contribution to the discussion of Diaconis and Freedman’s “On the consistency of Bayes estimates”. Annals of Statistics 14, 49–55.CrossRefGoogle Scholar
  11. Hjort, N. L. (1987). Semiparametric Bayes estimators. Proceedings of the First World Congress of the Bernoulli Society, VNU Science Press.Google Scholar
  12. Hjort, N. L. (1988). Contribution to the discussion of Hinkley’s lectures on bootstrapping techniques. Scandinavian Journal of Statistics, to appear.Google Scholar
  13. Hjort, N. L. (1990a). Goodness of fit tests in models for life history data based on cumulative hazard rates. Annals of Statistics 18, 1221–1258.MathSciNetzbMATHCrossRefGoogle Scholar
  14. Hjort, N. L. (1990b). Nonparametric Bayes estimators based on Beta processes in models for life history data. Annals of Statistics 14, 1259–1294.MathSciNetCrossRefGoogle Scholar
  15. Hjort, N. L. (1991a). On inference in parametric survival data models. International Statistical Review. To appear.Google Scholar
  16. Hjort, N. L. (1991b). Bayesian and empirical Bayesian bootstrapping. Paper presented at the Fourth València meeting on Bayesian Statistics. Statistical Research Report, Department of Mathematics, University of Oslo.Google Scholar
  17. Hjort, N. L. (1991c). Estimation in moderately misspecified models. Statistical Research Report, Department of Mathematics, University of Oslo.Google Scholar
  18. Olkin, I. and Spiegelman, C. H. (1987). A semiparametric approach to density estimation. Journal of American Statistical Association 82, 858–865.MathSciNetzbMATHCrossRefGoogle Scholar
  19. Ramlau-Hansen, H. (1983). Smoothing counting process intensities by means of kernel functions. Annals of Statistics 11, 453–466.MathSciNetzbMATHCrossRefGoogle Scholar
  20. Tanner, M. A. and Wong, W. H. (1983). The estimation of the hazard function from randomly censored data. Annals of Statistics 11, 989–993.MathSciNetzbMATHCrossRefGoogle Scholar
  21. Yandell, B. S. (1983). Nonparametric inference for rates and densities with censored serial data. Annals of Statistics 11, 1119–1135.MathSciNetzbMATHGoogle Scholar

Additional References

  1. Escobar, M. D. and West, M. (1991) Bayesian prediction and density estimation, ISDS Discussion Paper #90-A16, Duke University.Google Scholar
  2. West, M. (1992) Modelling with mixtures (with discussion). In Bayesian Statistics 4. (J. O. Berger, J. M. Bernardo, A. P. Dawid and A. F. M. Smith, Eds.), Oxford University Press, Oxford.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1992

Authors and Affiliations

  • Nils Lid Hjort
    • 1
  • Mike West
    • 2
  • Sue Leurgans
    • 3
  1. 1.Department of Mathematics and StatisticsUniversity of OsloOsloNorway
  2. 2.Institute of Statistics & Decision SciencesDuke UniversityDurhamUSA
  3. 3.Department of StatisticsThe Ohio State UniversityColumbusUSA

Personalised recommendations