Two-stage Bayesian model choice and analysis of screening experiments

WANG Jian-jun, MAYi-zhong, WANG Xin

Systems Engineering - Theory & Practice ›› 2011, Vol. 31 ›› Issue (8) : 1447-1453.

PDF(667 KB)
PDF(667 KB)
Systems Engineering - Theory & Practice ›› 2011, Vol. 31 ›› Issue (8) : 1447-1453. DOI: 10.12011/1000-6788(2011)8-1447

Two-stage Bayesian model choice and analysis of screening experiments

  • WANG Jian-jun1, MAYi-zhong1, WANG Xin2
Author information +
History +

Abstract

As for fractional factorial experiment design with non-normal responses, a method of two-stage Bayesian model choice was proposed in the paper when the number of the factors in screening experiments is large. Firstly, the MCMC method was used to simulate dynamically the Markov Chain of every parameter’s posterior distribution in generalized linear models, and the significant level of the factors was identified according to the Bayesian posterior probability of every parameter which is more than or less than zero, then initial current model and candidate models were obtained by the significant level of these factors. Secondly, the significant factors were identified to establish a model with best short-term predictions by means of the Bayesian model assessment criterion based on the deviance information criterion (DIC), which was used to stepwise optimize the output from the current model and candidate models. Finally, a practical industrial example reveals that the proposed method can identify effectively significant factors in fractional factorial experiment design with non-normal responses.

Key words

generalized linear models / non-normal response / fractional factorial experiment design / Bayesian analysis

Cite this article

Download Citations
WANG Jian-jun, MAYi-zhong, WANG Xin. Two-stage Bayesian model choice and analysis of screening experiments. Systems Engineering - Theory & Practice, 2011, 31(8): 1447-1453 https://doi.org/10.12011/1000-6788(2011)8-1447

References

[1] Myers R H, Montgomery D C. A tutorial on generalized linear models[J]. Journal of Quality Technology, 1997, 29(3): 274-291.

[2] Bisgarrd S, Fuller H T. Analysis of factorial experiments with defects or defectives as the response[J]. Quality Engineering, 1994, 7(2): 429-443.

[3] Wu C F J, Hamada M. Experiments: Planning, Analysis and Parameter Design Optimization[M]. New York: John Wiley, 2000.

[4] 何桢, 马彦辉, 赵有. 非正态响应的部分因子试验设计[J]. 工业工程, 2008, 11(2): 72-75. He Z, Ma Y H, Zhao Y. On fractional factorial experiment design with non-normal response[J]. Industrial Engineering Journal, 2008, 11(2): 72-75.

[5] Lewis S L, Montgomery D C, Myers R H. Examples of designed experiments with nonnormal responses[J]. Journal of Quality Technology, 2001, 33(3): 265-278.

[6] Lewis S L, Montgomery D C, Myers R H. The analysis of designed experiments with non-normal response[J]. Quality Engineering, 1999, 12(2): 225-243.

[7] Weaver B P, Hamada M S. A Bayesian approach to the analysis of industrial experiments: An illustration with binomial count data[J]. Quality Engineering, 2008, 20(3): 269-280.

[8] Robinson T J, Anderson-Cook C M, Hamada M S. Bayesian analysis of split-plot experiments with nonnormal responses for evaluating nonstandard performance criteria[J]. Journal of Quality Technology, 2009, 51(1): 56-64.

[9] Woodward P,Walley R. Bayesian variable selection for fractional factorial experiments with multilevel categorical factors[J]. Journal of Quality Technology, 2009, 41(3): 228-240.

[10] 汪建均, 马义中, 汪新. 广义线性模型的贝叶斯分析及稳健参数设计应用[J].系统工程, 2009, 27(4): 71-77. Wang J J, Ma Y Z, Wang, X. Bayesian analysis of generalized linear models and its application in robust parameter design[J]. Systems Engineering 2009, 27(4): 71-77.

[11] McCullagh P, Nelder J A. Generalized Linear Models[M]. London: Chapman and Hall, 1989.

[12] Myers R H, Montgomery D C, Vining G G. Generalized Linear Models: With Applications in Engineering and the Sciences[M]. New York: John Wiley & Sons, 2002.

[13] Ibrahim J G, Laud P W. On Bayesian analysis of generalized linear models using Jeffreys’ prior[J]. Journal of the American Statistical Association, 1991, 86: 981-986.

[14] Ntzoufras I. Bayesian Modeling Using WinBUGS[M]. New York: John Wiley & Sons, 2009.

[15] Spiegelhalter D J, Best N G, Carlin B P, et al. Bayesian measures of model complexity and fit[J]. Journal of the Royal Statistical Society, Series B, 2002, 64(4): 583-616.
PDF(667 KB)

320

Accesses

0

Citation

Detail

Sections
Recommended

/