Global Sensitivity Analysis with Dependence Measures

Abstract : Global sensitivity analysis with variance-based measures suffers from several theoretical and practical limitations, since they focus only on the variance of the output and handle multivariate variables in a limited way. In this paper, we introduce a new class of sensitivity indices based on dependence measures which overcomes these insufficiencies. Our approach originates from the idea to compare the output distribution with its conditional counterpart when one of the input variables is fixed. We establish that this comparison yields previously proposed indices when it is performed with Csiszar f-divergences, as well as sensitivity indices which are well-known dependence measures between random variables. This leads us to investigate completely new sensitivity indices based on recent state-of-the-art dependence measures, such as distance correlation and the Hilbert-Schmidt independence criterion. We also emphasize the potential of feature selection techniques relying on such dependence measures as alternatives to screening in high dimension.
Document type :
Preprints, Working Papers, ...
Liste complète des métadonnées

Cited literature [64 references]  Display  Hide  Download
Contributor : Sébastien Da Veiga <>
Submitted on : Monday, November 11, 2013 - 12:57:23 PM
Last modification on : Tuesday, January 22, 2019 - 3:51:42 PM
Document(s) archivé(s) le : Wednesday, February 12, 2014 - 4:29:24 AM


Files produced by the author(s)


  • HAL Id : hal-00903283, version 1
  • ARXIV : 1311.2483



Sébastien Da Veiga. Global Sensitivity Analysis with Dependence Measures. 2013. ⟨hal-00903283⟩



Record views


Files downloads