Global sensitivity analysis with dependence measures

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 depende...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of statistical computation and simulation Jg. 85; H. 7; S. 1283 - 1305
1. Verfasser: Da Veiga, Sebastien
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Abingdon Taylor & Francis 03.05.2015
Taylor & Francis Ltd
Schlagworte:
Computer simulation
Correlation analysis
Criteria
Dimensional measurements
global sensitivity analysis
Handles
Hilbert space
independence
kernel
Mathematical models
Mathematics
Multivariate analysis
mutual information
Random variables
Screening
Sensitivity analysis
State of the art
Statistics
Global sensitivity analysis
Independance
Kernel
Mutual information
ISSN:0094-9655, 1563-5163
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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 Csiszár 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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0094-9655
1563-5163
DOI:10.1080/00949655.2014.945932