Weighted space-filling designs

Many computer models or simulators have probabilistic dependencies between their input variables, which if not accounted for during design selection may result in a large numbers of simulator runs being required for analysis. We propose a method that incorporates known dependencies between input variables into design selection for simulators and demonstrate the benefits of this approach via a simulator for atmospheric dispersion. We quantify the benefit of the new techniques over standard space-filling and Monte Carlo simulation. The proposed methods are adaptations of computer-generated spread and coverage space-filling designs, with ‘distance’ between two input points redefined to include a weight function. This weight function reflects any known multivariate dependencies between input variables and prior information on the design region. The methods can include quantitative and qualitative variables, and different types of prior information. Novel graphical methods, adapted from fraction of design space plots, are used to assess and compare the designs.

[1]  A. O'Hagan,et al.  Bayesian calibration of computer models , 2001 .

[2]  Luc Pronzato,et al.  Design of computer experiments: space filling and beyond , 2011, Statistics and Computing.

[3]  Jack P. C. Kleijnen,et al.  Simulation experiments in practice: statistical design and regression analysis , 2007, J. Simulation.

[4]  David M. Steinberg,et al.  Fast Computation of Designs Robust to Parameter Uncertainty for Nonlinear Settings , 2009, Technometrics.

[5]  M. E. Johnson,et al.  Minimax and maximin distance designs , 1990 .

[6]  Kit Po Wong,et al.  Differential Evolution, an Alternative Approach to Evolutionary Algorithm , 2006, Proceedings of the 13th International Conference on, Intelligent Systems Application to Power Systems.

[7]  Antony M. Overstall,et al.  A Strategy for Bayesian Inference for Computationally Expensive Models with Application to the Estimation of Stem Cell Properties , 2013, Biometrics.

[8]  Dick den Hertog,et al.  Constrained Maximin Designs for Computer Experiments , 2003, Technometrics.

[9]  Stefano Tarantola,et al.  Uncertainty in Industrial Practice , 2008 .

[10]  Tarantola Stefano,et al.  Uncertainty in Industrial Practice - A Guide to Quantitative Uncertainty Management , 2008 .

[11]  Peter Z. G. Qian,et al.  Gaussian Process Models for Computer Experiments With Qualitative and Quantitative Factors , 2008, Technometrics.

[12]  R. K. Meyer,et al.  The Coordinate-Exchange Algorithm for Constructing Exact Optimal Experimental Designs , 1995 .

[13]  W. Briggs.  Statistical Methods in the Atmospheric Sciences , 2007 .

[14]  Thomas J. Santner,et al.  Non-collapsing Space-filling Designs for Bounded Non-rectangular Regions , 2011 .

[15]  C. Lemieux.  Monte Carlo and Quasi-Monte Carlo Sampling , 2009 .

[16]  Lotfi A. Zadeh,et al.  Please Scroll down for Article International Journal of General Systems Fuzzy Sets and Systems* Fuzzy Sets and Systems* , 2022 .

[17]  R. H. Myers,et al.  Fraction of Design Space to Assess Prediction Capability of Response Surface Designs , 2003 .

[18]  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.

[19]  Thomas J. Santner,et al.  Noncollapsing Space-Filling Designs for Bounded Nonrectangular Regions , 2012, Technometrics.

[20]  Derek Bingham,et al.  Handbook of Design and Analysis of Experiments , 2015 .

[21]  J. Andrew Royle,et al.  Exchange algorithms for constructing large spatial designs , 2002 .

[22]  R. D. Cook,et al.  A Comparison of Algorithms for Constructing Exact D-Optimal Designs , 1980 .

[23]  Tim B. Swartz,et al.  Approximating Integrals Via Monte Carlo and Deterministic Methods , 2000 .

[24]  E J Bedrick,et al.  Estimating the Mahalanobis Distance from Mixed Continuous and Discrete Data , 2000, Biometrics.

[25]  Robert E. Shannon,et al.  Design and analysis of simulation experiments , 1978, WSC '78.

[26]  André I. Khuri.  Designs for Generalized Linear Models , 2011, International Encyclopedia of Statistical Science.

[27]  D. Steinberg,et al.  Technometrics , 2008 .

[28]  David J. Thomson,et al.  The U.K. Met Office's Next-Generation Atmospheric Dispersion Model, NAME III , 2007 .

[29]  Theodore T. Allen.  Introduction to Discrete Event Simulation and Agent-based Modeling: Voting Systems, Health Care, Military, and Manufacturing , 2011 .

[30]  R. Iman,et al.  A distribution-free approach to inducing rank correlation among input variables , 1982 .

[31]  William J. Welch,et al.  Uniform Coverage Designs for Molecule Selection , 2002, Technometrics.

[32]  O. L. Davies,et al.  The Design and Analysis of Experiments , 1953 .

[33]  V. R. Joseph,et al.  Minimum Energy Designs : From Nanostructure Synthesis to Sequential Optimization , 2009 .

[34]  Sonja Kuhnt,et al.  Design and analysis of computer experiments , 2010 .

[35]  Marc C. Kennedy,et al.  Case studies in Gaussian process modelling of computer codes , 2006, Reliab. Eng. Syst. Saf..

[36]  Mohamed A. El-Sharkawi,et al.  Modern heuristic optimization techniques :: theory and applications to power systems , 2008 .

[37]  R. Pearl.  Biometrics , 1914, The American Naturalist.

[38]  Bertrand Iooss,et al.  Latin hypercube sampling with inequality constraints , 2009, 0909.0329.