AN EFFICIENT SEQUENTIAL DESIGN FOR SENSITIVITY EXPERIMENTS

doi:10.1016/S0252-9602(10)60044-6

Abstract

Abstract:

In sensitivity experiments, the response is binary and each experimental unit has a critical stimulus level that cannot be observed directly. It is often of interest to estimate extreme quantiles of the distribution of these
critical stimulus levels over the tested products. For this purpose a new sequential scheme is proposed with some commonly used models. By using the bootstrap repeated-sampling principle, reasonable prior
distributions based on a historic data set are specified. Then, a Bayesian strategy for the sequential procedure is provided and the estimator is given. Further, a high order approximation for such an estimator is explored and its consistency is proven. A simulation study shows that the proposed method gives superior performances over the existing methods.

Key words: sensitivity experiments, extreme quantiles, bootstrap principle, Bayesian strategy, sequential design

CLC Number:

62L05

TIAN Yu-Bin, FANG Yong-Fei. AN EFFICIENT SEQUENTIAL DESIGN FOR SENSITIVITY EXPERIMENTS[J].Acta mathematica scientia,Series B, 2010, 30(1): 269-280.

Trendmd

References

[1] Silvapulle M J. On the existence of maximum likelihood estimators for the binomial response model. Journal of the Royal Statistical Society, Ser B, 1981, 43: 310--313

[2] Wu C F J. Efficient sequential designs with binary data. J Amer Statist Assoc, 1985, 80: 974--84

[3] Tian Yubin, Li Guoying. Saddlepoint approach to inference for response probabilities. Journal of Statistical Planning and Inference, 2005, 133(2): 405--416

[4] Barry T Neyer. A d-optimality-based sensitivity test. Technometrics, 1994, 36: 61--70

[5] Joseph V R. Efficient Robbins-Monro procedure for binary data. Biometrika, 2004, 91: 461--470

[6] Kushner H J, Yin G G. Stochastic Approximation Algorithms and Applications. New york: Springer, 1997

[7] Joseph V R, Wu C F J. Operating window experiments: A novel approach to quality improvement. Journal of Quality Technology, 2002, 34: 345--354

[8] Wethrill G B. Sequential estimation of quanta-l response curves. Journal of the Royal Statistical Society, Ser B, 1963, 25, 1--48

[9] Joseph G Voelkel. Sequential Experimental Designs for Sensitivity Experiments. Rochester Institute of Technology: Technical Report, 1999

[10] ASTM. Standard Test Methods for Impact Resistance of Plastic Film by the Free-Falling Dart Method. Annual Book of ASTM Standards. Philadelphia: ASTM, 1995

[11] Chao M T, Fuh C D. Bootstrap method for the up and down test on pyrotechnology sensitivity analysis. Statistica Sinica, 2001, 11: 1--21

[12] Fu James C, Wang Liquan. A random-discretization based monte carlo sampling method and its applications. Methodology and Computing in Applied Probability, 2002, 4: 5--25

[13] Wong Winghung, Li Bing. Laplace expansion for posterior densities of nonlinear functions of parameters. Biometrika, 1992, 79: 393--398

[14] Barndoff-Nielsen O E, Cox D R. Asymptotic Technology for Use in Statistics. London: Chapman and Hall, 1989

[15] Datta S. A uniform L1 law of large numbers for functions on a totally bounded metric space. Sankhya, Series A, 1997, 59: 167--174

[16] Tian Yubin, Zhang Ying, Li Guoying. Saddlepoint approximate confidence intervals for the p-th quantile of logistic response distribution. Acta Mathematica Scientia, 2005, 25A(1): 110--118