Back to Search Start Over

Structure learning for extremal tree models

Authors :
Engelke, Sebastian
Volgushev, Stanislav
Publication Year :
2020

Abstract

Extremal graphical models are sparse statistical models for multivariate extreme events. The underlying graph encodes conditional independencies and enables a visual interpretation of the complex extremal dependence structure. For the important case of tree models, we develop a data-driven methodology for learning the graphical structure. We show that sample versions of the extremal correlation and a new summary statistic, which we call the extremal variogram, can be used as weights for a minimum spanning tree to consistently recover the true underlying tree. Remarkably, this implies that extremal tree models can be learned in a completely non-parametric fashion by using simple summary statistics and without the need to assume discrete distributions, existence of densities, or parametric models for bivariate distributions.

Subjects

Subjects :
Statistics - Methodology

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2012.06179
Document Type :
Working Paper