On assessing independence of Competing Risks when failure times are discrete
- 1 January 1996
- journal article
- Published by Springer Nature in Lifetime Data Analysis
- Vol. 2 (2) , 195-209
- https://doi.org/10.1007/bf00128575
Abstract
The traditional approach to modelling for Competing Risks, via a multivariate distribution of latent failure times, is very natural for many applications but suffers from a well-documented problem of identifiability. However, the demonstrations of this problem in the literature apply to essentially continuous latent failure times where any atoms of probability in their distributions are not too intrusive. It is shown in this paper that for discrete failure times the classic results on the identifiability problem concerning the existence of equivalent independent risks are incomplete.Keywords
This publication has 20 references indexed in Scilit:
- Dependent failure analysisReliability Engineering & System Safety, 1991
- The identifiability of the competing risks modelBiometrika, 1989
- Practical Problems in the Statistical Analysis of Reliability DataJournal of the Royal Statistical Society Series C: Applied Statistics, 1989
- The Binomial Failure Rate Common Cause ModelTechnometrics, 1986
- Maximum Likelihood Estimation for a Discrete Multivariate Shock ModelJournal of the American Statistical Association, 1983
- On constant-sum models for censored survival dataBiometrika, 1979
- Converting Dependent Models into Independent ones, Preserving Essential FeaturesThe Annals of Probability, 1978
- A Note on Independence of Multivariate Lifetimes in Competing Risks ModelsThe Annals of Statistics, 1977
- A Multivariate Exponential DistributionJournal of the American Statistical Association, 1967
- A Bivariate Extension of the Exponential DistributionJournal of the American Statistical Association, 1961