Using EM and Data Augmentation for the Competing Risks Model

  title={Using EM and Data Augmentation for the Competing Risks Model},
  author={Radu V. Craiu and Thierry Duchesne},
We consider a survival analysis problem in which items are subject to failure from competing risks. For some of the items, the failure cause is known only to belong to a subset of the set of all possible causes, while for the remaining items the cause of death is known precisely. In this chapter we investigate two complementary analyses based on models in which the hazard rates are assumed piecewise constant. The approaches proposed rely on the EM algorithm and its Bayesian counterpart, the… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 34 references

Markov beta and gamma processes for modelling hazard rates

  • L. E. Nieto-Barajas, S. G. Walker
  • Scandinavian Journal of Statistics
  • 2002
Highly Influential
5 Excerpts

Survival with competing risks and masked causes of failures

  • B. J. Flehinger, B. Reiser, E. Yashchin
  • Biometrika
  • 1998
Highly Influential
7 Excerpts

A note on a test for competing risks with missing failure

  • A. Dewanji
  • type. Biometrika
  • 1992
Highly Influential
4 Excerpts

Bayesian Data Analysis, second edition

  • A. Gelman, J. B. Carlin, H. S. Stern, D. B. Rubin
  • 2003
1 Excerpt

Bayesian analysis of competing risks with partially masked cause of failure

  • S. Base, A. Sen, M. Bannered
  • Applied Statistics
  • 2003
1 Excerpt

Analysis of competing risks by using bayesian smoothing

  • D. Gasbarra, S. R. Karia
  • Scandinavian Journal of Statistics 27,
  • 2000
2 Excerpts

Similar Papers

Loading similar papers…