2020/06/15 by Ivano Azzini, Azzini, Ivano, Thierry A. Mara +3
Decision Sciences · Engineering · #Applications (stat.AP) #FOS: Computer and information sciences #Fatigue and fracture mechanics #Machine Learning (stat.ML) #Nuclear and radioactivity studies #Probabilistic and Robust Engineering Design
paper · pdf · doi:10.48550/arxiv.2006.08232
openalex publication_date 2020/06/15 · openalex created_date 2023/09/17 · openalex updated_date 2026/07/28
This study compares the performances of two sampling-based strategies for the simultaneous estimation of the first-and total-orders variance-based sensitivity indices (a.k.a Sobol' indices). The first strategy was introduced by [8] and is the current approach employed by practitioners. The second one was only recently introduced by the authors of the present article. They both rely on different estimators of first-and total-orders Sobol' indices. The asymp-totic normal variances of the two sets of estimators are established and their accuracies are compared theoretically and numerically. The results show that the new strategy outperforms the current one.Keywords: global sensitivity analysis, variance-based sensitivity indices, first-order Sobol' index, total-order Sobol' index, Monte Carlo estimate, asymptotic normality