Optimization over a finite number of system designs with one-stage sampling and multiple comparisons with the best

Jason C. Hsu*, Barry L. Nelson

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Scopus citations

Abstract

The authors present an alternative to standard ranking and selection methods for stochastic optimization problems when the number of system designs is finite. Extensions of the MCB (multiple comparisons with the best) methodology that would be useful in simulation experiments include methods for applying MCB in steady-state simulation using single-run experiment designs and theory for sharpening MCB inference by using the common-random-numbers variance-reduction technique. Examples are given.

Original languageEnglish (US)
Title of host publicationWinter Simul Conf Proc 1988
PublisherPubl by IEEE
Pages451-457
Number of pages7
ISBN (Print)0911801421, 9780911801422
DOIs
StatePublished - 1988
EventWinter Simulation Conference Proceedings - 1988 - San Diego, CA, USA
Duration: Dec 12 1988Dec 14 1988

Publication series

NameWinter Simulation Conference Proceedings
ISSN (Print)0275-0708

Other

OtherWinter Simulation Conference Proceedings - 1988
CitySan Diego, CA, USA
Period12/12/8812/14/88

ASJC Scopus subject areas

  • Software
  • Modeling and Simulation
  • Safety, Risk, Reliability and Quality
  • Chemical Health and Safety
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Optimization over a finite number of system designs with one-stage sampling and multiple comparisons with the best'. Together they form a unique fingerprint.

Cite this