Affordable Access

deepdyve-link
Publisher Website

A Common Rationale for Global Sensitivity Measures and Their Estimation.

Authors
  • Borgonovo, Emanuele1
  • Hazen, Gordon B2
  • Plischke, Elmar3
  • 1 Department of Decision Sciences, Bocconi University, Milan, Italy. , (Italy)
  • 2 Department of Industrial Engineering and Management Science and Engineering, Northwestern University, Evanston, IL, USA.
  • 3 Clausthal University of Technology, Clausthal-Zellerfeld, Germany. , (Germany)
Type
Published Article
Journal
Risk analysis : an official publication of the Society for Risk Analysis
Publication Date
Oct 01, 2016
Volume
36
Issue
10
Pages
1871–1895
Identifiers
DOI: 10.1111/risa.12555
PMID: 26857789
Source
Medline
Keywords
License
Unknown

Abstract

Measures of sensitivity and uncertainty have become an integral part of risk analysis. Many such measures have a conditional probabilistic structure, for which a straightforward Monte Carlo estimation procedure has a double-loop form. Recently, a more efficient single-loop procedure has been introduced, and consistency of this procedure has been demonstrated separately for particular measures, such as those based on variance, density, and information value. In this work, we give a unified proof of single-loop consistency that applies to any measure satisfying a common rationale. This proof is not only more general but invokes less restrictive assumptions than heretofore in the literature, allowing for the presence of correlations among model inputs and of categorical variables. We examine numerical convergence of such an estimator under a variety of sensitivity measures. We also examine its application to a published medical case study.

Report this publication

Statistics

Seen <100 times