Generalized Hoeffding-Sobol Decomposition for Dependent Variables -Application to Sensitivity Analysis
Statistics Theory
2012-03-14 v3 Statistics Theory
Abstract
In this paper, we consider a regression model built on dependent variables. This regression modelizes an input output relationship. Under boundedness assumptions on the joint distribution function of the input variables, we show that a generalized Hoeffding-Sobol decomposition is available. This leads to new indices measuring the sensitivity of the output with respect to the input variables. We also study and discuss the estimation of these new indices.
Cite
@article{arxiv.1112.1788,
title = {Generalized Hoeffding-Sobol Decomposition for Dependent Variables -Application to Sensitivity Analysis},
author = {Gaëlle Chastaing and Fabrice Gamboa and Clémentine Prieur},
journal= {arXiv preprint arXiv:1112.1788},
year = {2012}
}