New improvements in the use of dependence measures for sensitivity analysis and screening

DOI10.1080/00949655.2016.1149854zbMATH Open1462.49068arXiv1412.1414OpenAlexW2279261944MaRDI QIDQ5221514FDOQ5221514

Authors: Matthias De Lozzo, Amandine Marrel 

Publication date: 1 April 2020

Published in: Journal of Statistical Computation and Simulation (Search for Journal in Brave)

Abstract: Physical phenomena are commonly modeled by numerical simulators. Such codes can take as input a high number of uncertain parameters and it is important to identify their influences via a global sensitivity analysis (GSA). However, these codes can be time consuming which prevents a GSA based on the classical Sobol' indices, requiring too many simulations. This is especially true as the number of inputs is important. To address this limitation, we consider recent advances in dependence measures, focusing on the distance correlation and the Hilbert-Schmidt independence criterion (HSIC). Our objective is to study these indices and use them for a screening purpose. Numerical tests reveal some differences between dependence measures and classical Sobol' indices, and preliminary answers to "What sensitivity indices to what situation?" are derived. Then, two approaches are proposed to use the dependence measures for a screening purpose. The first one directly uses these indices with independence tests; asymptotic tests and their spectral extensions exist and are detailed. For a higher accuracy in presence of small samples, we propose a non-asymptotic version based on bootstrap sampling. The second approach is based on a linear model associating two simulations, which explains their output difference as a weighed sum of their input differences. From this, a bootstrap method is proposed for the selection of the influential inputs. We also propose a heuristic approach for the calibration of the HSIC Lasso method. Numerical experiments are performed and show the potential of these approaches for screening when many inputs are not influential.

Full work available at URL: https://arxiv.org/abs/1412.1414

Recommendations

• Global sensitivity analysis with dependence measures
• A screening approach for non-parametric global sensitivity analysis
• Review of global sensitivity analysis of numerical models
• Estimation of global sensitivity indices for models with dependent variables
• Generalized Hoeffding-Sobol decomposition for dependent variables -- application to sensitivity analysis

zbMATH Keywords

bootstrapsensitivity analysisscreeningdependence measuresindependence testsHSIC

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Applications of statistics in engineering and industry; control charts (62P30) Statistical ranking and selection procedures (62F07) Sensitivity analysis for optimization problems on manifolds (49Q12) Numerical methods for variational inequalities and related problems (65K15)

Cites Work

• Measuring and testing dependence by correlation of distances
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing
• Least angle regression. (With discussion)
• Title not available (Why is that?)
• Title not available (Why is that?)
• The design and analysis of computer experiments.
• Regularization and Variable Selection Via the Elastic Net
• High-Dimensional Feature Selection by Feature-Wise Kernelized Lasso
• Ridge Regression: Biased Estimation for Nonorthogonal Problems
• Theory of Reproducing Kernels
• Algorithmic Learning Theory
• Searching for important factors in simulation models with many factors: Sequential bifurcation
• Title not available (Why is that?)
• Global sensitivity analysis: The primer
• Encyclopedia of Distances
• Global sensitivity measures from given data
• Title not available (Why is that?)
• Global sensitivity analysis with dependence measures
• Sampling plans based on balanced incomplete block designs for evaluating the importance of computer model inputs
• Sensitivity analysis and related analyses: A review of some statistical techniques
• Fast Kernel-Based Independent Component Analysis
• Derivative-based global sensitivity measures: general links with Sobol' indices and numerical tests
• Randomized pick-freeze for sparse Sobol indices estimation in high dimension

Cited In (8)

• Fast prediction of aquifer thermal energy storage: a multicyclic metamodelling procedure
• New sensitivity analysis subordinated to a contrast
• Global Sensitivity Analysis for Optimization with Variable Selection
• Crossed-derivative based sensitivity measures for interaction screening
• A new dependence measure for importance analysis: application to an environmental model
• Global sensitivity analysis with dependence measures
• Kernel-based Sensitivity Analysis for (Excursion) Sets
• A screening approach for non-parametric global sensitivity analysis

Uses Software

• tree-structured-covariance

This page was built for publication: New improvements in the use of dependence measures for sensitivity analysis and screening

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5221514)