Sensitivity measures,anova-like Techniques and the use of bootstrap

Abstract Sobol' sensitivity indices,used in variance based global sensitivity analysis of model output,are compared with the Analysis of Variance in classical factorial design. Monte Carlo computation of Sobol' indices is described briefly, and a bootstrap approach is presented,which can be used to produce a confidence interval for the true,unknown indices. Keywords: Analysis of variance decompositionbootstrapsensitivity indices