Factor screening for simulation with multiple responses

Sequential bifurcation

W. Shi, J.P.C. Kleijnen, Z. Liu

Research output: Contribution to journalArticleScientificpeer-review

Abstract

The goal of factor screening is to find the really important inputs (factors) among the many inputs that may be changed in a realistic simulation experiment. A specific method is sequential bifurcation (SB), which is a sequential method that changes groups of inputs simultaneously. SB is most efficient and effective if the following assumptions are satisfied: (i) second-order polynomials are adequate approximations of the input/output functions implied by the simulation model; (ii) the signs of all first-order effects are known; and (iii) if two inputs have no important first-order effects, then they have no important second-order effects either (heredity property). This paper examines SB for random simulation with multiple responses (outputs), called multi-response SB (MSB). This MSB selects groups of inputs such that—within a group—all inputs have the same sign for a specific type of output, so no cancellation of first-order effects occurs. To obtain enough replicates (replications) for correctly classifying a group effect or an individual effect as being important or unimportant, MSB applies Wald’s sequential probability ratio test (SPRT). The initial number of replicates in this SPRT is also selected efficiently by MSB. Moreover, MSB includes a procedure to validate the three assumptions of MSB. The paper evaluates the performance of MSB through extensive Monte Carlo experiments that satisfy all MSB assumptions, and through a case study representing a logistic system in China; the results are very promising.
Original languageEnglish
Pages (from-to)136-147
JournalEuropean Journal of Operational Research
Volume237
Issue number1
DOIs
Publication statusPublished - 16 Aug 2014

Fingerprint

Multiple Responses
Screening
Bifurcation
Logistics
Simulation
Experiments
Polynomials
Sequential Probability Ratio Test
First-order
Output
Sequential Methods
Factors
Monte Carlo Experiment
Cancellation
Replication
Simulation Experiment
China
Simulation Model
Polynomial
Evaluate

Keywords

  • simulation
  • design of experiments
  • statistical analysis

Cite this

@article{0a46c030032149d29513e020fe10c997,
title = "Factor screening for simulation with multiple responses: Sequential bifurcation",
abstract = "The goal of factor screening is to find the really important inputs (factors) among the many inputs that may be changed in a realistic simulation experiment. A specific method is sequential bifurcation (SB), which is a sequential method that changes groups of inputs simultaneously. SB is most efficient and effective if the following assumptions are satisfied: (i) second-order polynomials are adequate approximations of the input/output functions implied by the simulation model; (ii) the signs of all first-order effects are known; and (iii) if two inputs have no important first-order effects, then they have no important second-order effects either (heredity property). This paper examines SB for random simulation with multiple responses (outputs), called multi-response SB (MSB). This MSB selects groups of inputs such that—within a group—all inputs have the same sign for a specific type of output, so no cancellation of first-order effects occurs. To obtain enough replicates (replications) for correctly classifying a group effect or an individual effect as being important or unimportant, MSB applies Wald’s sequential probability ratio test (SPRT). The initial number of replicates in this SPRT is also selected efficiently by MSB. Moreover, MSB includes a procedure to validate the three assumptions of MSB. The paper evaluates the performance of MSB through extensive Monte Carlo experiments that satisfy all MSB assumptions, and through a case study representing a logistic system in China; the results are very promising.",
keywords = "simulation, design of experiments, statistical analysis",
author = "W. Shi and J.P.C. Kleijnen and Z. Liu",
year = "2014",
month = "8",
day = "16",
doi = "10.1016/j.ejor.2014.02.021",
language = "English",
volume = "237",
pages = "136--147",
journal = "European Journal of Operational Research",
issn = "0377-2217",
publisher = "Elsevier Science BV",
number = "1",

}

Factor screening for simulation with multiple responses : Sequential bifurcation. / Shi, W.; Kleijnen, J.P.C.; Liu, Z.

In: European Journal of Operational Research, Vol. 237, No. 1, 16.08.2014, p. 136-147.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Factor screening for simulation with multiple responses

T2 - Sequential bifurcation

AU - Shi, W.

AU - Kleijnen, J.P.C.

AU - Liu, Z.

PY - 2014/8/16

Y1 - 2014/8/16

N2 - The goal of factor screening is to find the really important inputs (factors) among the many inputs that may be changed in a realistic simulation experiment. A specific method is sequential bifurcation (SB), which is a sequential method that changes groups of inputs simultaneously. SB is most efficient and effective if the following assumptions are satisfied: (i) second-order polynomials are adequate approximations of the input/output functions implied by the simulation model; (ii) the signs of all first-order effects are known; and (iii) if two inputs have no important first-order effects, then they have no important second-order effects either (heredity property). This paper examines SB for random simulation with multiple responses (outputs), called multi-response SB (MSB). This MSB selects groups of inputs such that—within a group—all inputs have the same sign for a specific type of output, so no cancellation of first-order effects occurs. To obtain enough replicates (replications) for correctly classifying a group effect or an individual effect as being important or unimportant, MSB applies Wald’s sequential probability ratio test (SPRT). The initial number of replicates in this SPRT is also selected efficiently by MSB. Moreover, MSB includes a procedure to validate the three assumptions of MSB. The paper evaluates the performance of MSB through extensive Monte Carlo experiments that satisfy all MSB assumptions, and through a case study representing a logistic system in China; the results are very promising.

AB - The goal of factor screening is to find the really important inputs (factors) among the many inputs that may be changed in a realistic simulation experiment. A specific method is sequential bifurcation (SB), which is a sequential method that changes groups of inputs simultaneously. SB is most efficient and effective if the following assumptions are satisfied: (i) second-order polynomials are adequate approximations of the input/output functions implied by the simulation model; (ii) the signs of all first-order effects are known; and (iii) if two inputs have no important first-order effects, then they have no important second-order effects either (heredity property). This paper examines SB for random simulation with multiple responses (outputs), called multi-response SB (MSB). This MSB selects groups of inputs such that—within a group—all inputs have the same sign for a specific type of output, so no cancellation of first-order effects occurs. To obtain enough replicates (replications) for correctly classifying a group effect or an individual effect as being important or unimportant, MSB applies Wald’s sequential probability ratio test (SPRT). The initial number of replicates in this SPRT is also selected efficiently by MSB. Moreover, MSB includes a procedure to validate the three assumptions of MSB. The paper evaluates the performance of MSB through extensive Monte Carlo experiments that satisfy all MSB assumptions, and through a case study representing a logistic system in China; the results are very promising.

KW - simulation

KW - design of experiments

KW - statistical analysis

UR - http://www.sciencedirect.com/science/article/pii/S0377221714001362

U2 - 10.1016/j.ejor.2014.02.021

DO - 10.1016/j.ejor.2014.02.021

M3 - Article

VL - 237

SP - 136

EP - 147

JO - European Journal of Operational Research

JF - European Journal of Operational Research

SN - 0377-2217

IS - 1

ER -