On the performance characteristics of a closed adaptive sequential procedure for selecting the best bernoulli population
- 1 January 1983
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics. Part C: Sequential Analysis
- Vol. 1 (4) , 315-354
- https://doi.org/10.1080/07474948308836021
Abstract
In a recent paper, Bechhofer and Kulkarni proposed closed adaptive sequential procedures for a general class of k—population Bernoulli selection goals. These sequential selection procedures achieve the same probability of a correct selection, uniformly in the unknown single—trail "success" probabilities , as do the corresponding single—stage selection procedures which take exactly n observations from each of the k populations. The sequential procedures always require less (often substantially less) than kn observations to terminate experimentation. This earlier paper described the procedures, discussed their performance in general terms, and cited several of their optimality properties. In the present paper we specialize these procedures, and focus on the particular goal of selecting the population associated with p[k] where are the ordered .Stronger optimality results than those given in our earlier paper are cited. We give exact numerical results for such performance characteristics of the sequential procedure (p*) as the distribution of the total number of observations N (i) taken from the population associated with and the total number of observations taken from all k populations, when the procedure terminates sampling. A simple upper bound for is given. These results along with other related ones will assist the potential user of the sequential procedure in assessing its merits relative to those of other competing procedures.Keywords
This publication has 5 references indexed in Scilit:
- On the Performance Characteristics of a Closed Adaptive Sequential Procedure for Selecting the Best Bernoulli Population.Published by Defense Technical Information Center (DTIC) ,1982
- Multi-Armed Bandits with Discount Factor Near One: The Bernoulli CaseThe Annals of Statistics, 1981
- On the order statistics from equally correlated normal random variablesBiometrika, 1973
- Selecting the Best One of Several Binomial PopulationsBell System Technical Journal, 1957
- A Single-Sample Multiple Decision Procedure for Ranking Means of Normal Populations with known VariancesThe Annals of Mathematical Statistics, 1954