Abstract
Consider the problem of finding the points of maximum of an expectation functional over a finite setS. Based on statistical estimates at each point ofS, confidence sets for theargmax-set are constructed which guarantee a prespecified probability of correct selection. We review known selection methods and propose a new two-stage procedure that works well for largeS and few global maxima. The performance is compared in a simulation study.
Similar content being viewed by others
References
R.E. Bechhofer, A single-sample multiple decision procedure for ranking means of normal populations with known variances, Ann. Math. Stat. 25 (1954) 16.
R.E. Bechhofer and D.M. Goldsman, A comparison of the performances of procedures for selecting the normal population having the largest mean when the variances are known and equal, in:Contributions to Probability and Statistics: Essays in Honor of I. Olkin, eds. L.J. Gleser et al. (Springer, New York, 1989).
A. Futschik, Confidence intervals for the maximum of a regression function with multiple peaks, in:Proc. 10th Int. Conf. on Probability and Mathematical Statistics, eds. A. Pázman and J. Volaufová, Bratislava (1991).
J.D. Gibbons, I. Olkin and M. Sobel,Selecting and Ordering Populations (Wiley, New York, 1977).
S.S. Gupta, On some multiple decision (selection and ranking) rules, Technometrics 7 (1965) 225.
S.S. Gupta and S. Panchapakesan,Multiple Decision Procedures: Theory and Methodology of Selecting and Ranking Populations (Wiley, New York, 1979).
Y. Hochberg and A.C. Tamhane,Multiple Comparison Procedures (Wiley, New York, 1987).
A.J. King, Stochastic programming problems: examples from the literature, in:Numerical Techniques for Stochastic Optimization, eds. Yu. Ermoliev and R.J.-B. Wets (Springer, New York, 1988).
V. Norkin, Y. Ermoliev and A. Ruszczyński, On optimal allocation of indivisibles under uncertainty, Working Paper WP-94-21, Int. Inst. f. Applied Systems Analysis, Laxenburg, Austria (1994).
R.D. Reiss,Approximate Distributions of Order Statistics (Springer, New York, 1989).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Futschik, A., Pflug, G. Confidence sets for discrete stochastic optimization. Ann Oper Res 56, 95–108 (1995). https://doi.org/10.1007/BF02031702
Issue Date:
DOI: https://doi.org/10.1007/BF02031702