Global sensitivity analysis with dependence measures
From MaRDI portal
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.
Recommendations
- New improvements in the use of dependence measures for sensitivity analysis and screening
- The \(f\)-sensitivity index
- Estimation of global sensitivity indices for models with dependent variables
- Generalized Hoeffding-Sobol decomposition for dependent variables -- application to sensitivity analysis
- Shapley Effects for Global Sensitivity Analysis: Theory and Computation
Cites work
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 1425054 (Why is no real title available?)
- scientific article; zbMATH DE number 5055767 (Why is no real title available?)
- scientific article; zbMATH DE number 3252891 (Why is no real title available?)
- A Hilbert Space Embedding for Distributions
- A Mathematical Theory of Communication
- A Selective Overview of Variable Selection in High Dimensional Feature Space (Invited Review Article)
- A least-squares approach to direct importance estimation
- ANOVA kernels and RKHS of zero mean functions for model-based sensitivity analysis
- Algorithmic Learning Theory
- Association of Random Variables, with Applications
- Asymptotic normality and efficiency of two Sobol index estimators
- Better estimation of small Sobol' sensitivity indices
- Comparing clusterings -- an information based distance
- Density ratio estimation in machine learning. Foreword by Thomas G. Dietterich
- Derivative based global sensitivity measures and their link with global sensitivity indices
- Distance covariance in metric spaces
- Efficient estimation of sensitivity indices
- Energy statistics: a class of statistics based on distances
- Equivalence of distance-based and RKHS-based statistics in hypothesis testing
- Feature screening via distance correlation learning
- Feature selection via dependence maximization
- Global sensitivity analysis for a numerical model of radionuclide migration from the RRC ``Kurchatov Institute radwaste disposal site
- High-Dimensional Feature Selection by Feature-Wise Kernelized Lasso
- Integral Probability Metrics and Their Generating Classes of Functions
- Kernel methods for measuring independence
- Measuring and testing dependence by correlation of distances
- New sensitivity analysis subordinated to a contrast
- Nonparametric functional data analysis. Theory and practice.
- Nonparametric independence screening in sparse ultra-high-dimensional additive models
- On the empirical estimation of integral probability metrics
- On the use of variance reducing multipliers in Monte Carlo computations of a global sensitivity index
- Probabilistic Sensitivity Analysis of Complex Models: A Bayesian Approach
- Sampling plans based on balanced incomplete block designs for evaluating the importance of computer model inputs
- Sensitivity indices for multivariate outputs
- Some Concepts of Dependence
- Sparse additive models
- Statistical consistency of kernel canonical correlation analysis
- Sure independence screening for ultrahigh dimensional feature space. With discussion and authors' reply
- The distance correlation \(t\)-test of independence in high dimension
- Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity index
Cited in
(34)- Goal-oriented Shapley effects with special attention to the quantile-oriented case
- Emulated multivariate global sensitivity analysis for complex computer models applied to agricultural simulators
- Fast prediction of aquifer thermal energy storage: a multicyclic metamodelling procedure
- Randomized Global Sensitivity Analysis and Model Robustness
- Simultaneous estimation of complementary moment independent and reliability-oriented sensitivity measures
- Global sensitivity of structural variability by random sampling
- Global Sensitivity Analysis for Optimization with Variable Selection
- Copula theory and probabilistic sensitivity analysis: is there a connection?
- Sensitivity analysis based on Cramér-von Mises distance
- Global sensitivity analysis: a novel generation of mighty estimators based on rank statistics
- Model predictivity assessment: incremental test-set selection and accuracy evaluation
- A new methodology based on covariance and HDMR for global sensitivity analysis
- Explaining classifiers with measures of statistical association
- The \(f\)-sensitivity index
- A new dependence measure for importance analysis: application to an environmental model
- Sensitivity analysis: a review of recent advances
- Global sensitivity analysis and Wasserstein spaces
- Sliced Gradient-Enhanced Kriging for High-Dimensional Function Approximation
- Global sensitivity analysis for statistical model parameters
- Reliability of global sensitivity indices
- Moving least squares based sensitivity analysis for models with dependent variables
- Kernel-based Sensitivity Analysis for (Excursion) Sets
- Projected Gaussian Markov improvement algorithm for high-dimensional discrete optimization via simulation
- Estimation of the derivative-based global sensitivity measures using a Gaussian process metamodel
- New improvements in the use of dependence measures for sensitivity analysis and screening
- Forward-reverse switch between density-based and regional sensitivity analysis
- Derivative Based Global Sensitivity Analysis and Its Entropic Link
- Nonparametric estimation of probabilistic sensitivity measures
- Estimation of global sensitivity indices for models with dependent variables
- Generalized Hoeffding-Sobol decomposition for dependent variables -- application to sensitivity analysis
- Goal-oriented sensitivity analysis of hyperparameters in deep learning
- A Generalized Kernel Method for Global Sensitivity Analysis
- Covariance constraints for stochastic inverse problems of computer models
- Total effects with constrained features
This page was built for publication: Global sensitivity analysis with dependence measures
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5220789)
