Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates

被引：4120

作者：

Sobol, IM ^{[1
]}

机构：

[1] Russian Acad Sci, Inst Math Modelling, Moscow 125047, Russia

来源：

MATHEMATICS AND COMPUTERS IN SIMULATION | 2001年 / 55卷 / 1-3期

关键词：

sensitivity analysis; Monte Carlo method; quasi-Monte Carlo method; mathematical modelling;

D O I：

10.1016/S0378-4754(00)00270-6

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Global sensitivity indices for rather complex mathematical models can be efficiently computed by Monte Carlo (or quasi-Monte Carlo) methods. These indices are used for estimating the influence of individual variables or groups of variables on the model output. (C) 2001 IMACS. Published by Elsevier Science B.V. All rights reserved.

引用

页码：271 / 280

页数：10

共 16 条

[11]

Saltenis V, 1982, OPTIMAL DECISION THE, V8, P124

[12]

Sobol I.M., 1993, Mathematical Modeling and Computational Experiment, V1, P407

[13] On quasi-Monte Carlo integrations [J].

Sobol, IM .

MATHEMATICS AND COMPUTERS IN SIMULATION, 1998, 47 (2-5) :103-112

[14]

Sobol IM, 1996, VESTN MOSK U MAT M+, P92

[15] On the use of variance reducing multipliers in Monte Carlo computations of a global sensitivity index [J].

Sobol', IM ;

Levitan, YL .

COMPUTER PHYSICS COMMUNICATIONS, 1999, 117 (1-2) :52-61

[16]

SOBOL LM, 1969, MULTIDIMENSIONAL QUA

← 1 2 →