Estimation of global sensitivity indices for models with dependent variables

被引：235
作者：
Kucherenko, S. [1 ,2 ]
Tarantola, S. [2 ]
Annoni, P. [2 ]
机构：
[1] Univ London Imperial Coll Sci Technol & Med, London SW7 2AZ, England
[2] European Commiss, Joint Res Ctr, I-21027 Ispra, VA, Italy
来源：
COMPUTER PHYSICS COMMUNICATIONS | 2012年 / 183卷 / 04期
基金：
英国工程与自然科学研究理事会;
关键词：
Global sensitivity analysis; Correlated inputs; Gaussian copula; Quasi Monte Carlo methods; Sobol' sensitivity indices; Sobol' sequences; MATHEMATICAL-MODELS; UNCERTAINTY;
D O I：
10.1016/j.cpc.2011.12.020
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
A novel approach for estimation variance-based sensitivity indices for models with dependent variables is presented. Both the first order and total sensitivity indices are derived as generalizations of Sobol' sensitivity indices. Formulas and Monte Carlo numerical estimates similar to Sobol' formulas are derived. A copula-based approach is proposed for sampling from arbitrary multivariate probability distributions. A good agreement between analytical and numerical values of the first order and total indices for considered test cases is obtained. The behavior of sensitivity indices depends on the relative predominance of interactions and correlations. The method is shown to be efficient and general. C) 2011 Elsevier B.V. All rights reserved.
引用
收藏
页码：937 / 946
页数：10
相关论文
共 29 条
[1]   Evidence synthesis, parameter correlation and probabilistic sensitivity analysis [J].
Ades, AE ;
Claxton, K ;
Sculpher, M .
HEALTH ECONOMICS, 2006, 15 (04) :373-381
[2]  
[Anonymous], P 2 INT S SENS AN MO
[3]   IMPLEMENTING SOBOLS QUASIRANDOM SEQUENCE GENERATOR [J].
BRATLEY, P ;
FOX, BL .
ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 1988, 14 (01) :88-100
[4]   An efficient algorithm to accelerate the discovery of complex material formulations [J].
Brell, George ;
Li, Genyuan ;
Rabitz, Herschel .
JOURNAL OF CHEMICAL PHYSICS, 2010, 132 (17)
[5]  
Cherubini U, 2004, COPULA METHODS FINAN
[6]   Local Polynomial Estimation for Sensitivity Analysis on Models With Correlated Inputs [J].
Da Veiga, Sebastien ;
Wahl, Francois ;
Gamboa, Fabrice .
TECHNOMETRICS, 2009, 51 (04) :452-463
[7]  
FERSON S, 1995, BIOL CONSERV, V73, P101, DOI 10.1016/0006-3207(95)00047-8
[8]  
Ishigami T., 1990, P 1 INT S UNC MOD AN, P398, DOI [10.1109/ISUMA.1990.151285, DOI 10.1109/ISUMA.1990.151285]
[9]   Sensitivity analysis in presence of model uncertainty and correlated inputs [J].
Jacques, Julien ;
Lavergne, Christian ;
Devictor, Nicolas .
RELIABILITY ENGINEERING & SYSTEM SAFETY, 2006, 91 (10-11) :1126-1134
[10]  
JANSEN MJW, 1994, PREDICTABILITY AND NONLINEAR MODELLING IN NATURAL SCIENCES AND ECONOMICS, P334
123