A perspective on variance reduction in dynamic simulation experiments

Barry L. Nelson

doi:10.1080/03610918708812597

A perspective on variance reduction in dynamic simulation experiments

Barry L. Nelson^*

^*Corresponding author for this work

Industrial Engineering and Management Sciences

Research output: Contribution to journal › Article › peer-review

35 Scopus citations

Abstract

A unifying perspective on variance reduction is presented that emphasizes broadly defined variance reduction strategies rather than specific variance reduction techniques (VRTs). The perspective is based on a new taxonomy of VRTs, which is reviewed in detail. The variance reduction problem is formulated as a constrained optimization problem, and results that guarantee the effectiveness of variance reduction strategies are summarized.

Original language	English (US)
Pages (from-to)	385-426
Number of pages	42
Journal	Communications in Statistics - Simulation and Computation
Volume	16
Issue number	2
DOIs	https://doi.org/10.1080/03610918708812597
State	Published - Jan 1 1987

Keywords

Latin hypercube sampling
Monte Carlo
Russian roulette
antithetic variates
common random numbers
conditional expectations
control variates
generalized semi-Markov process
importance sampling
indirect estimators
poststratifying the sample
sampling
simulation
splitting
stratified sampling
swindle
systematic sampling
variance reduction

ASJC Scopus subject areas

Statistics and Probability
Modeling and Simulation

Access to Document

10.1080/03610918708812597

Cite this

@article{7114b95eba2a4d6a90dfc395ba73e6f7,

title = "A perspective on variance reduction in dynamic simulation experiments",

abstract = "A unifying perspective on variance reduction is presented that emphasizes broadly defined variance reduction strategies rather than specific variance reduction techniques (VRTs). The perspective is based on a new taxonomy of VRTs, which is reviewed in detail. The variance reduction problem is formulated as a constrained optimization problem, and results that guarantee the effectiveness of variance reduction strategies are summarized.",

keywords = "Latin hypercube sampling, Monte Carlo, Russian roulette, antithetic variates, common random numbers, conditional expectations, control variates, generalized semi-Markov process, importance sampling, indirect estimators, poststratifying the sample, sampling, simulation, splitting, stratified sampling, swindle, systematic sampling, variance reduction",

author = "Nelson, {Barry L.}",

note = "Funding Information: This research was partially supported by a University Seed Grant from the Office of Research and Graduate Studies, The Ohio State University. The author benefited from discussions with Bruce Schmeiser of Purdue University and the reviews of J.P.C. Kleijnen and two referees.",

year = "1987",

month = jan,

day = "1",

doi = "10.1080/03610918708812597",

language = "English (US)",

volume = "16",

pages = "385--426",

journal = "Communications in Statistics Part B: Simulation and Computation",

issn = "0361-0918",

publisher = "Taylor and Francis Ltd.",

number = "2",

}

TY - JOUR

T1 - A perspective on variance reduction in dynamic simulation experiments

AU - Nelson, Barry L.

N1 - Funding Information: This research was partially supported by a University Seed Grant from the Office of Research and Graduate Studies, The Ohio State University. The author benefited from discussions with Bruce Schmeiser of Purdue University and the reviews of J.P.C. Kleijnen and two referees.

PY - 1987/1/1

Y1 - 1987/1/1

N2 - A unifying perspective on variance reduction is presented that emphasizes broadly defined variance reduction strategies rather than specific variance reduction techniques (VRTs). The perspective is based on a new taxonomy of VRTs, which is reviewed in detail. The variance reduction problem is formulated as a constrained optimization problem, and results that guarantee the effectiveness of variance reduction strategies are summarized.

AB - A unifying perspective on variance reduction is presented that emphasizes broadly defined variance reduction strategies rather than specific variance reduction techniques (VRTs). The perspective is based on a new taxonomy of VRTs, which is reviewed in detail. The variance reduction problem is formulated as a constrained optimization problem, and results that guarantee the effectiveness of variance reduction strategies are summarized.

KW - Latin hypercube sampling

KW - Monte Carlo

KW - Russian roulette

KW - antithetic variates

KW - common random numbers

KW - conditional expectations

KW - control variates

KW - generalized semi-Markov process

KW - importance sampling

KW - indirect estimators

KW - poststratifying the sample

KW - sampling

KW - simulation

KW - splitting

KW - stratified sampling

KW - swindle

KW - systematic sampling

KW - variance reduction

UR - http://www.scopus.com/inward/record.url?scp=0000941398&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0000941398&partnerID=8YFLogxK

U2 - 10.1080/03610918708812597

DO - 10.1080/03610918708812597

M3 - Article

AN - SCOPUS:0000941398

VL - 16

SP - 385

EP - 426

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 2

ER -

A perspective on variance reduction in dynamic simulation experiments

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this