Theorems and examples on high dimensional model representation

被引:352
作者
Sobol, IM [1 ]
机构
[1] Russian Acad Sci, Inst Math Modelling, Moscow 125047, Russia
关键词
analysis of variances; high dimensional model representation; global sensitivity indices;
D O I
10.1016/S0951-8320(02)00229-6
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Mathematical models described by multivariable functions f(x) where x = (x(1),...,x(n)) are investigated. If the model output is influenced mainly by low order combinations of input variables x(1),...,x(n), an attempt can be made to construct a low order approximation to the model using values of f(x) only. (C) 2002 Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:187 / 193
页数:7
相关论文
共 9 条
  • [1] Sensitivity measures, ANOVA-like techniques and the use of bootstrap
    Archer, GEB
    Saltelli, A
    Sobol, IM
    [J]. JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 1997, 58 (02) : 99 - 120
  • [2] CHAN K, 1998, P SAMO 98 VEN OFF PU
  • [3] Efficient input-output model representations
    Rabitz, H
    Alis, ÖF
    Shorter, J
    Shim, K
    [J]. COMPUTER PHYSICS COMMUNICATIONS, 1999, 117 (1-2) : 11 - 20
  • [4] About the use of rank transformation in sensitivity analysis of model output
    Saltelli, A
    Sobol, IM
    [J]. RELIABILITY ENGINEERING & SYSTEM SAFETY, 1995, 50 (03) : 225 - 239
  • [5] Saltelli A, 1995, MATEMATICHESKOE MODE, V7
  • [6] Sobol I.M., 1969, Multidimensional quadrature formulas and Haar functions
  • [7] Sobol I.M., 1993, Mathematical Modeling and Computational Experiment, V1, P407
  • [8] SOBOL IM, 1996, VESTNIK MOSK U M, V6, P92
  • [9] SOBOL IM, 1967, SOV MATH DOKL, V8, P810