Skip to Main content Skip to Navigation
Journal articles

Dimension reduction in multivariate extreme value analysis

Abstract : Non-parametric assessment of extreme dependence structures between an arbitrary number of variables, though quite well-established in dimension 2 and recently extended to moderate dimensions such as 5, still represents a statistical challenge in larger dimensions. Here, we propose a novel approach that combines clustering techniques with angular/spectral measure analysis to find groups of variables (not necessarily disjoint) exhibiting asymptotic dependence, thereby reducing the dimension of the initial problem. A heuristic criterion is proposed to choose the threshold over which it is acceptable to consider observations as extreme and the appropriate number of clusters. When empirically evaluated through numerical experiments, the approach we promote here is found to be very efficient under some regularity constraints, even in dimension 20. For illustration purpose, we also carry out a case study in dietary risk assessment.
Document type :
Journal articles
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download

https://hal-mines-paristech.archives-ouvertes.fr/hal-01256008
Contributor : Bibliothèque Mines Paristech <>
Submitted on : Thursday, January 14, 2016 - 11:32:05 AM
Last modification on : Thursday, September 24, 2020 - 4:34:19 PM
Long-term archiving on: : Saturday, April 16, 2016 - 10:24:17 AM

File

euclid.ejs.1426611768.pdf
Publisher files allowed on an open archive

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Emilie Chautru. Dimension reduction in multivariate extreme value analysis. Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2015, 9 (1), pp.383-418. ⟨10.1214/15-EJS1002⟩. ⟨hal-01256008⟩

Share

Metrics

Record views

316

Files downloads

547