Metamodel construction for sensitivity analysis
ESAIM. Proceedings, Tome 60 (2017), pp. 27-69
Cet article a éte moissonné depuis la source EDP Sciences
We propose to estimate a metamodel and the sensitivity indices of a complex model m in the Gaussian regression framework. Our approach combines methods for sensitivity analysis of complex models and statistical tools for sparse non-parametric estimation in multivariate Gaussian regression model. It rests on the construction of a metamodel for aproximating the Hoeffding-Sobol decomposition of m. This metamodel belongs to a reproducing kernel Hilbert space constructed as a direct sum of Hilbert spaces leading to a functional ANOVA decomposition. The estimation of the metamodel is carried out via a penalized least-squares minimization allowing to select the subsets of variables that contribute to predict the output. It allows to estimate the sensitivity indices of m. We establish an oracle-type inequality for the risk of the estimator, describe the procedure for estimating the metamodel and the sensitivity indices, and assess the performances of the procedure via a simulation study.
Affiliations des auteurs :
Sylvie Huet 1 ; Marie-Luce Taupin 2, 1
@article{EP_2017_60_a2,
author = {Sylvie Huet and Marie-Luce Taupin},
title = {Metamodel construction for sensitivity analysis},
journal = {ESAIM. Proceedings},
pages = {27--69},
year = {2017},
volume = {60},
doi = {10.1051/proc/201760027},
language = {en},
url = {http://geodesic.mathdoc.fr/articles/10.1051/proc/201760027/}
}
Sylvie Huet; Marie-Luce Taupin. Metamodel construction for sensitivity analysis. ESAIM. Proceedings, Tome 60 (2017), pp. 27-69. doi: 10.1051/proc/201760027
Cité par Sources :