An overview of newer, advanced screening methods for the initial phase in an experimental design

Screening is the first phase of an experimental study on systems and simulation models. Its purpose is to eliminate negligible factors so that efforts may be concentrated upon just the important ones. Successfully screening of more than about 20 or 30 factors has been investigated only in the past 10 or 15 years with most improvements in the past 5 years. A handful of alternative methods including sequential bifurcation, iterated fractional factorial designs, and the Trocine Screening Procedure are described and evaluative and comparative results are presented.

[1]  Douglas C. Montgomery,et al.  Analysis of Supersaturated Designs , 2003 .

[2]  Jack P. C. Kleijnen,et al.  Searching for important factors in simulation models with many factors: Sequential bifurcation , 1997 .

[3]  Linda Trocine,et al.  An efficient, effective, and robust procedure for screening more than 20 independent variables employing a genetic algorithm , 2001 .

[4]  Douglas C. Montgomery,et al.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[5]  R. Cheng Searching For Important Factors: Sequential Bifurcation Under Uncertainty , 1997, Winter Simulation Conference Proceedings,.

[6]  Karen A. F. Copeland Experiments: Planning, Analysis, and Parameter Design Optimization , 2002 .

[7]  Carl A Mauro,et al.  Factor Screening in Simulation: Evaluation of Two Strategies Based on Random Balance Sampling , 1984 .

[8]  Douglas C. Montgomery,et al.  Multiple response surface methods in computer simulation , 1977 .

[9]  Terry Andres Sampling methods and sensitivity analysis for large parameter sets , 1997 .

[10]  Mansooreh Mollaghasemi,et al.  Comparison of a two-stage group-screening design to a standard 2k-p design for a whole-line semiconductor manufacturing simulation model , 1999, WSC '99.

[11]  Russell C. H. Cheng Searching for important factors: sequential bifurcation under uncertainty , 1997, WSC '97.

[12]  J. E. Jacoby,et al.  Multi‐variable experimentation and simulation models , 1962 .

[13]  Dennis K. J. Lin A new class of supersaturated designs , 1993 .

[14]  C. A. Mauro On the Performance of Two-Stage Group Screening Experiments , 1984 .