For the nonparametric estimation of a survival function when censoring is present, the Kaplan-Meier estimator is often used. The admissibility of this estimator and other related maximum likelihood estimators is demonstrated. This is done by reducing the problem to one involving just the multinomial distribution and then using the stepwise Bayes technique to prove admissibility.
Publié le : 1989-12-14
Classification:
Kaplan-Meier estimator,
admissibility,
maximum likelihood,
censoring,
multinomial distribution,
stepwise Bayes,
62G05,
62C15
@article{1176347379,
author = {Meeden, G. and Ghosh, M. and Srinivasan, C. and Vardeman, S.},
title = {The Admissibility of the Kaplan-Meier and other Maximum Likelihood Estimators in the Presence of Censoring},
journal = {Ann. Statist.},
volume = {17},
number = {1},
year = {1989},
pages = { 1509-1531},
language = {en},
url = {http://dml.mathdoc.fr/item/1176347379}
}
Meeden, G.; Ghosh, M.; Srinivasan, C.; Vardeman, S. The Admissibility of the Kaplan-Meier and other Maximum Likelihood Estimators in the Presence of Censoring. Ann. Statist., Tome 17 (1989) no. 1, pp. 1509-1531. http://gdmltest.u-ga.fr/item/1176347379/