Integrated variance reduction strategies for simulation
Integrated variance reduction strategies for simulation
We develop strategies for integrated use of certain well-known variance reduction techniques to estimate a mean response in a finite-horizon simulation experiment. The building blocks for these integrated variance reduction strategies are the techniques of conditional expectation, correlation induction (including antithetic variates and Latin hypercube sampling), and control variates; all pairings of these techniques are examined. For each integrated strategy, we establish sufficient conditions under which that strategy will yield a smaller response variance than its constituent variance reduction techniques will yield individually. We also provide asymptotic variance comparisons between many of the methods discussed, with emphasis on integrated strategies that incorporate Latin hypercube sampling. An experimental performance evaluation reveals that in the simulation of stochastic activity networks, substantial variance reductions can be achieved with these integrated strategies. Both the theoretical and experimental results indicate that superior performance is obtained via joint application of the techniques of conditional expectation and Latin hypercube sampling.
simulation, design of experiments, antithetic variates, latin hypercube sampling simulation, efficiency, conditioning, control variates, correlation induction simulation, statistical analysis, combined Monte Carlo methods
327-346
Avramidis, Athanassios.N.
d6c4b6b6-c0cf-4ed1-bbe1-a539937e4001
Wilson, James R.
938b5976-c9c4-42a5-8ec9-4b36266347bb
March 1996
Avramidis, Athanassios.N.
d6c4b6b6-c0cf-4ed1-bbe1-a539937e4001
Wilson, James R.
938b5976-c9c4-42a5-8ec9-4b36266347bb
Avramidis, Athanassios.N. and Wilson, James R.
(1996)
Integrated variance reduction strategies for simulation.
Operations Research, 44 (2), .
(doi:10.1287/opre.44.2.327).
Abstract
We develop strategies for integrated use of certain well-known variance reduction techniques to estimate a mean response in a finite-horizon simulation experiment. The building blocks for these integrated variance reduction strategies are the techniques of conditional expectation, correlation induction (including antithetic variates and Latin hypercube sampling), and control variates; all pairings of these techniques are examined. For each integrated strategy, we establish sufficient conditions under which that strategy will yield a smaller response variance than its constituent variance reduction techniques will yield individually. We also provide asymptotic variance comparisons between many of the methods discussed, with emphasis on integrated strategies that incorporate Latin hypercube sampling. An experimental performance evaluation reveals that in the simulation of stochastic activity networks, substantial variance reductions can be achieved with these integrated strategies. Both the theoretical and experimental results indicate that superior performance is obtained via joint application of the techniques of conditional expectation and Latin hypercube sampling.
This record has no associated files available for download.
More information
Published date: March 1996
Keywords:
simulation, design of experiments, antithetic variates, latin hypercube sampling simulation, efficiency, conditioning, control variates, correlation induction simulation, statistical analysis, combined Monte Carlo methods
Organisations:
Mathematical Sciences
Identifiers
Local EPrints ID: 336779
URI: http://eprints.soton.ac.uk/id/eprint/336779
ISSN: 0030-364X
PURE UUID: 3d5e3036-bcac-4bd0-b754-07fa483f5f4a
Catalogue record
Date deposited: 13 Apr 2012 08:54
Last modified: 15 Mar 2024 03:29
Export record
Altmetrics
Contributors
Author:
James R. Wilson
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
