Non-parametric adaptive estimation of order 1 Sobol indices in stochastic models, with an application to epidemiology

DOI10.1214/19-EJS1627MaRDI QIDQ2283588zbMATH OpenOpenAlexFDO

Authors Gwénaëlle Castellan, Anthony Cousien, Viet Chi Tran

Publication date 3 January 2020

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1611.07230, https://projecteuclid.org/euclid.ejs/1578042013

zbMATH Keywords

adaptive non-parametric inferenceapplications to epidemiologymodel selectionsensitivity analysis in a stochastic frameworkSIR modelSobol indices of order 1spread of the hepatitis virus C among drug userswarped wavelets

Mathematics Subject Classification ID

Sensitivity analysis for optimization problems on manifolds (49Q12) Nonparametric regression and quantile regression (62G08) Applications of statistics to biology and medical sciences; meta analysis (62P10) Epidemiology (92D30)

Abstract: Global sensitivity analysis is a set of methods aiming at quantifying the contribution of an uncertain input parameter of the model (or combination of parameters) on the variability of the response. We consider here the estimation of the Sobol indices of order 1 which are commonly-used indicators based on a decomposition of the output's variance. In a deterministic framework, when the same inputs always give the same outputs, these indices are usually estimated by replicated simulations of the model. In a stochastic framework, when the response given a set of input parameters is not unique due to randomness in the model, metamodels are often used to approximate the mean and dispersion of the response by deterministic functions. We propose a new non-parametric estimator without the need of defining a metamodel to estimate the Sobol indices of order 1. The estimator is based on warped wavelets and is adaptive in the regularity of the model. The convergence of the mean square error to zero, when the number of simulations of the model tend to infinity, is computed and an elbow effect is shown, depending on the regularity of the model. Applications in Epidemiology are carried to illustrate the use of non-parametric estimators.

Recommendations

• Risk of estimators for Sobol' sensitivity indices based on metamodels
• Asymptotic normality and efficiency of two Sobol index estimators
• Randomized Sobol' sensitivity indices
• On the consistency of Sobol indices with respect to stochastic ordering of model parameters
• Uncertainty quantification: a minimum variance unbiased (joint) estimator of the non-normalized Sobol' indices

Cites work

• Adaptive estimation of a quadratic functional by model selection.
• Analysis of variance designs for model output
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Efficient estimation of sensitivity indices
• Estimation of the Sobol indices in a linear functional multidimensional model
• Global sensitivity analysis of stochastic computer models with joint metamodels
• Global sensitivity analysis: The primer
• scientific article; zbMATH DE number 1529823 (Why is no real title available?)
• scientific article; zbMATH DE number 1425054 (Why is no real title available?)
• Introduction to nonparametric estimation
• Mathematical tools for understanding infectious disease dynamics.
• Non-parametric estimation of the first-order Sobol indices with bootstrap bandwidth
• PenalizationversusGoldenshluger − Lepski strategies in warped bases regression
• Rates of convergence in conditional covariance matrix with nonparametric entries estimation
• Regression in random design and warped wavelets
• Stochastic epidemic models and their statistical analysis
• Stochastic epidemic models with inference. Lectures given at the ICPAM/CIMPA school on stochastic models of epidemics, Ziguinchor, Senegal, December 5--16, 2015
• Sélection d'histogrammes à l'aide d'un critère de type Akaike
• UNCERTAINTIES ASSESSMENT IN GLOBAL SENSITIVITY INDICES ESTIMATION FROM METAMODELS
• Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity index
• Wavelets, approximation, and statistical applications

Cited in

(5)

• Non-parametric estimation of the first-order Sobol indices with bootstrap bandwidth
• On the consistency of Sobol indices with respect to stochastic ordering of model parameters
• A tutorial on Sobol' global sensitivity analysis applied to biological models
• A two-stage method for the estimation of global sensitivity indices of non-parametric models
• Multilevel Monte Carlo metamodeling for variance function estimation

This page was built for publication: Non-parametric adaptive estimation of order 1 Sobol indices in stochastic models, with an application to epidemiology

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2283588)