Using Orthogonal Arrays in the Sensitivity Analysis of Computer Models

We consider a class of input sampling plans, called permuted column sampling plans, that are popular in sensitivity analysis of computer models. Permuted column plans, including replicated Latin hypercube sampling, support estimation of first-order sensitivity coefficients, but these estimates are biased when the usual practice of random column permutation is used to construct the sampling arrays. Deterministic column permutations may be used to eliminate this estimation bias. We prove that any permuted column sampling plan that eliminates estimation bias, using the smallest possible number of runs in each array and containing the largest possible number of arrays, can be characterized by an orthogonal array of strength 2. We derive approximate standard errors of the first-order sensitivityindices for this sampling plan. We give two examples demonstrating the sampling plan, behavior of the estimates, and standard errors, along with comparative results based on other approaches.

[1]  A. Saltelli,et al.  Making best use of model evaluations to compute sensitivity indices , 2002 .

[2]  Stefano Tarantola,et al.  Random balance designs for the estimation of first order global sensitivity indices , 2006, Reliab. Eng. Syst. Saf..

[3]  K. Shuler,et al.  Nonlinear sensitivity analysis of multiparameter model systems , 1977 .

[4]  Michael D. McKay,et al.  Evaluating Prediction Uncertainty , 1995 .

[5]  I. Sobol,et al.  Sensitivity Measures, ANOVA-like Techniques and the Use of Bootstrap , 1997 .

[6]  Boxin Tang.  Orthogonal Array-Based Latin Hypercubes , 1993 .

[7]  Karl Pearson,et al.  Mathematical contributions to the theory of evolution, On the law of ancestral heredity , 1898, Proceedings of the Royal Society of London.

[8]  Max D. Morris,et al.  Sampling plans based on balanced incomplete block designs for evaluating the importance of computer model inputs , 2006 .

[9]  Lih-Yuan Deng,et al.  Orthogonal Arrays: Theory and Applications , 1999, Technometrics.

[10]  A. W. Kemp,et al.  Kendall's Advanced Theory of Statistics. , 1994 .

[11]  A. O'Hagan,et al.  Probabilistic sensitivity analysis of complex models: a Bayesian approach , 2004 .

[12]  A. Owen.  Controlling correlations in latin hypercube samples , 1994 .

[13]  M. Kendall,et al.  Kendall's advanced theory of statistics , 1995 .

[14]  H. Niederreiter,et al.  Monte Carlo and Quasi-Monte Carlo Methods in Scientific Computing , 1995 .

[15]  Damaraju Raghavarao.  Random Balance Designs , 2004 .

[16]  C. Fortuin,et al.  Study of the sensitivity of coupled reaction systems to uncertainties in rate coefficients. I Theory , 1973 .

[17]  Peter C. Young,et al.  State Dependent Parameter metamodelling and sensitivity analysis , 2007, Comput. Phys. Commun..

[18]  F. E. Satterthwaite.  Random Balance Experimentation , 1959 .

[19]  M. Stein.  Large sample properties of simulations using latin hypercube sampling , 1987 .

[20]  Saltelli Andrea,et al.  Sensitivity Analysis for Nonlinear Mathematical Models. Numerical ExperienceSensitivity Analysis for Nonlinear Mathematical Models. Numerical Experience , 1995 .

[21]  W. Hoeffding.  A Class of Statistics with Asymptotically Normal Distribution , 1948 .

[22]  T. J. Mitchell,et al.  Bayesian Prediction of Deterministic Functions, with Applications to the Design and Analysis of Computer Experiments , 1991 .

[23]  Richard J. Beckman,et al.  A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code , 2000, Technometrics.

[24]  M.J.W. Jansen,et al.  Review of Saltelli, A. & Chan, K. & E.M.Scott (Eds) (2000), Sensitivity analysis. Wiley (2000) , 2001 .

[25]  R. J. Beckman,et al.  A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output... , 2000 .

[26]  Karl Pearson,et al.  Mathematical contributions to the theory of evolution.―On homotyposis in homologous but differentiated organs , 1903, Proceedings of the Royal Society of London.

[27]  I. Sobol,et al.  About the use of rank transformation in sensitivity analysis of model output , 1995 .