Sensitivity indices for independent groups of variables

DOI10.1016/J.MATCOM.2019.02.008MaRDI QIDQ6296372arXivWikidataFDO

Authors Baptiste Broto, François Bachoc, Marine Depecker, J. M. Martinez

Publication date 12 January 2018

Statistics (62-XX) Nonparametric inference (62Gxx) Parametric inference (62Fxx)

Abstract: In this paper, we study sensitivity indices for independent groups of variables and we look at the particular case of block-additive models. We show in this case that most of the Sobol indices are equal to zero and that Shapley effects can be estimated more efficiently. We then apply this study to Gaussian linear models, and we provide an efficient algorithm to compute the theoretical sensitivity indices. In numerical experiments, we show that this algorithm compares favourably to other existing methods. We also use the theoretical results to improve the estimation of the Shapley effects for general models, when the inputs form independent groups of variables.

This page was built for publication: Sensitivity indices for independent groups of variables

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6296372)