We present an asynchronous algorithm based on Quasi-Monte Carlo methods for the computation of multivari-ate integrals. Randomized Korobov and Richtmyer sequences are applied for problems of moderately high to high dimensions. We propose the use of Sobol rules in those dimensions where the integrand shows particular singular behavior. Timing results on MPI yield good speedup.

Abstract The Variogram Analysis of Response Surfaces (VARS) has been proposed by Razavi and Gupta as a new comprehensive framework in sensitivity analysis. According to these authors, VARS provides more intuitive notion is much computationally efficient than Sobol’ indices. Here we review arguments critically compare the performance VARS-TO, for total-order index, against Jansen estimator. We a...

Sensitivity analysis is a crucial tool in the development and evaluation of complex mathematical models. Sobol’s method is a variance-based global sensitivity analysis technique that has been applied to computational models to assess the relative importance of input parameters on the output. This paper introduces new notation that describes the Sobol indices in terms of the Pearson correlation ...

We report on the implementation of high dimensional scrambled Sobol sequences for Monte Carlo Simulations under the statistical software packages R and SPlus. The generator provides low discrepancy sequences distributed uniformly in [0, 1) or distributed normally with mean zero and variance one. The implementation interfaces the ACM Algorithm 659 which allows to generate three different types o...

Variance-based sensitivity analysis has been performed for a study of input parameters contribution into output variability of a largescale air pollution model the Unified Danish Eulerian Model. The problem of computing of numerical indicators of sensitivity Sobol’ global sensitivity indices leads to multidimensional integration. Plain and Adaptive Monte Carlo techniques for numerical integrati...