On Empirical Bayes Selection Rules for Negative Binomial Populations ( Unclassified ) 12 . PERSON / VL AUTHOR ( S )

This paper deals with the problem of selecting good negative binomial populations as compared with a standard or a control. The main results are based on the use of the empirical Bayes approach. First we derive the monotone empirical Bayes estimators of the concerned parameters. Based on these estimators, we construct monotone empirical Bayes selection rules. Asymptotic optimality properties of the monotone empirical Bayes estimators and the monotone empirical Bayes selection rules are investigated. The respective convergence rates for the estimation problem and for the selection problem are studied, under some conditions. AMS 1980 Subject Classification: Primary 62F07; Secondary 62C12.