Please use this identifier to cite or link to this item:
Title: Is VARS more intuitive and efficient than Sobol' indices?
Author: Puy, Arnald
Lo Piano, Samuele
Saltelli, Andrea
Others: Universitat Oberta de Catalunya (UOC)
Princeton University
University of Reading
University of Bergen
Keywords: Uncertainty
Modeling Statistics
Design of experiment
Sensitivity analysis
Issue Date: 2-Mar-2021
Publisher: Environmental Modelling & Software
Citation: Puy, A; Lo Piano, S; Saltelli, A.(2021). Is VARS more intuitive and efficient than Sobol¿ indices?, Environmental Modelling & Software,Volume 137,2021, 104960, ISSN 1364-8152.
Abstract: The Variogram Analysis of Response Surfaces (VARS) has been proposed by Razavi and Gupta as a new comprehensive framework in sensitivity analysis. According to these authors, VARS provides a more intuitive notion of sensitivity and is much more computationally efficient than Sobol¿ indices. Here we review these arguments and critically compare the performance of VARS-TO, for total-order index, against the total-order Jansen estimator. We argue that, unlike classic variance-based methods, VARS lacks a clear definition of what an ¿important¿ factor is, and we show that the alleged computational superiority of VARS does not withstand scrutiny. We conclude that while VARS enriches the spectrum of existing methods for sensitivity analysis, especially for a diagnostic use of mathematical models, it complements rather than replaces classic estimators used in variance-based sensitivity analysis.
Language: English
ISSN: 1364-8152MIAR
Appears in Collections:Articles cientÍfics

Files in This Item:
File Description SizeFormat 
Is VARS more intuitive and efficient than Sobol¿ indices.pdf2,47 MBAdobe PDFThumbnail