Using common random numbers in simulation experiments

an approach to statistical analysis

R. G. Heikes, Douglas Montgomery, R. L. Rardin

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

A widely applied method of experimental design in stochastic simulation is to use the same pseudo-random-number stream for each of the systems or alternatives to be compared. If there are only two alternatives, there is a well-known simple method of statistical analysis. This paper presents F. A. Graybill's extension of that analysis technique to the case of several systems or alternatives and points out its applicability in the simulation environment. The technique is illustrated using a stochastic simulation model of a small inventory system. An empirical comparison with other methods of design and analysis is included.

Original languageEnglish (US)
Pages (from-to)81-85
Number of pages5
JournalSimulation
Volume27
Issue number3
StatePublished - Sep 1976
Externally publishedYes

Fingerprint

Random number
Design of experiments
Simulation Experiment
Statistical Analysis
Statistical methods
Stochastic Simulation
Alternatives
Pseudorandom numbers
Experiments
Inventory Systems
Simulation Environment
Experimental design
Stochastic Model
Simulation Model

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Software
  • Safety, Risk, Reliability and Quality

Cite this

Using common random numbers in simulation experiments : an approach to statistical analysis. / Heikes, R. G.; Montgomery, Douglas; Rardin, R. L.

In: Simulation, Vol. 27, No. 3, 09.1976, p. 81-85.

Research output: Contribution to journalArticle

@article{e36568d017744d21b39c4aa1f802f8ce,
title = "Using common random numbers in simulation experiments: an approach to statistical analysis",
abstract = "A widely applied method of experimental design in stochastic simulation is to use the same pseudo-random-number stream for each of the systems or alternatives to be compared. If there are only two alternatives, there is a well-known simple method of statistical analysis. This paper presents F. A. Graybill's extension of that analysis technique to the case of several systems or alternatives and points out its applicability in the simulation environment. The technique is illustrated using a stochastic simulation model of a small inventory system. An empirical comparison with other methods of design and analysis is included.",
author = "Heikes, {R. G.} and Douglas Montgomery and Rardin, {R. L.}",
year = "1976",
month = "9",
language = "English (US)",
volume = "27",
pages = "81--85",
journal = "Simulation",
issn = "0037-5497",
publisher = "SAGE Publications Ltd",
number = "3",

}

TY - JOUR

T1 - Using common random numbers in simulation experiments

T2 - an approach to statistical analysis

AU - Heikes, R. G.

AU - Montgomery, Douglas

AU - Rardin, R. L.

PY - 1976/9

Y1 - 1976/9

N2 - A widely applied method of experimental design in stochastic simulation is to use the same pseudo-random-number stream for each of the systems or alternatives to be compared. If there are only two alternatives, there is a well-known simple method of statistical analysis. This paper presents F. A. Graybill's extension of that analysis technique to the case of several systems or alternatives and points out its applicability in the simulation environment. The technique is illustrated using a stochastic simulation model of a small inventory system. An empirical comparison with other methods of design and analysis is included.

AB - A widely applied method of experimental design in stochastic simulation is to use the same pseudo-random-number stream for each of the systems or alternatives to be compared. If there are only two alternatives, there is a well-known simple method of statistical analysis. This paper presents F. A. Graybill's extension of that analysis technique to the case of several systems or alternatives and points out its applicability in the simulation environment. The technique is illustrated using a stochastic simulation model of a small inventory system. An empirical comparison with other methods of design and analysis is included.

UR - http://www.scopus.com/inward/record.url?scp=0016993835&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0016993835&partnerID=8YFLogxK

M3 - Article

VL - 27

SP - 81

EP - 85

JO - Simulation

JF - Simulation

SN - 0037-5497

IS - 3

ER -