Empirical Bayes Estimation with Random Censoring
We study empirical Bayes estimation for exponential distributions based on randomly censored data. An empirical Bayes estimator φ̃n is constructed. The rate of asymptotic optimality of φ̃n is investigated. It is shown that under certain conditions, the regret of φ̃n converges to zero at a rate O(ln4n/n1/2), where n is the number of past data available when the present estimation problem is considered.
AMS Subject Classification62C12
KeywordsKaplan-Meier estimator Random censoring Rate of convergence Regret
Unable to display preview. Download preview PDF.