### Abstract

polynomial per output is an adequate approximation (valid metamodel) of the implicit input/output function of the underlying simulation model; (ii) the directions (signs) of the first-order effects are known (so the first-order polynomial approximation per output is monotonic); (iii) heredity applies; i.e., if an input has no important first-order effect, then this input has no important second-order effects. To validate these three assumptions, we develop new methods. We compare these methods through Monte Carlo experiments and a case study.

Original language | English |
---|---|

Place of Publication | Tilburg |

Publisher | CentER, Center for Economic Research |

Number of pages | 32 |

Volume | 2015-034 |

Publication status | Published - 17 Jun 2015 |

### Publication series

Name | CentER Discussion Paper |
---|---|

Volume | 2015-034 |

### Fingerprint

### Keywords

- simulation
- sensitivity analysis
- Design of experiments
- statistical analysis

### Cite this

*Validating the Assumptions of Sequential Bifurcation in Factor Screening*. (CentER Discussion Paper; Vol. 2015-034). Tilburg: CentER, Center for Economic Research.

}

**Validating the Assumptions of Sequential Bifurcation in Factor Screening.** / Shi, W.; Kleijnen, J.P.C.

Research output: Working paper › Discussion paper › Other research output

TY - UNPB

T1 - Validating the Assumptions of Sequential Bifurcation in Factor Screening

AU - Shi, W.

AU - Kleijnen, J.P.C.

PY - 2015/6/17

Y1 - 2015/6/17

N2 - Sequential bifurcation (SB) is a very efficient and effective method for identifying the important factors (inputs) of simulation models with very many factors, provided the SB assumptions are valid. A variant of SB called multiresponse SB (MSB) can be applied to simulation models with multiple types of responses (outputs). The specific SB and MSB assumptions are: (i) a second-orderpolynomial per output is an adequate approximation (valid metamodel) of the implicit input/output function of the underlying simulation model; (ii) the directions (signs) of the first-order effects are known (so the first-order polynomial approximation per output is monotonic); (iii) heredity applies; i.e., if an input has no important first-order effect, then this input has no important second-order effects. To validate these three assumptions, we develop new methods. We compare these methods through Monte Carlo experiments and a case study.

AB - Sequential bifurcation (SB) is a very efficient and effective method for identifying the important factors (inputs) of simulation models with very many factors, provided the SB assumptions are valid. A variant of SB called multiresponse SB (MSB) can be applied to simulation models with multiple types of responses (outputs). The specific SB and MSB assumptions are: (i) a second-orderpolynomial per output is an adequate approximation (valid metamodel) of the implicit input/output function of the underlying simulation model; (ii) the directions (signs) of the first-order effects are known (so the first-order polynomial approximation per output is monotonic); (iii) heredity applies; i.e., if an input has no important first-order effect, then this input has no important second-order effects. To validate these three assumptions, we develop new methods. We compare these methods through Monte Carlo experiments and a case study.

KW - simulation

KW - sensitivity analysis

KW - Design of experiments

KW - statistical analysis

M3 - Discussion paper

VL - 2015-034

T3 - CentER Discussion Paper

BT - Validating the Assumptions of Sequential Bifurcation in Factor Screening

PB - CentER, Center for Economic Research

CY - Tilburg

ER -