Graphical Models for Extremes

@article{Engelke2018GraphicalMF,
  title={Graphical Models for Extremes},
  author={Sebastian Engelke and Adrien Hitz},
  journal={arXiv: Statistics Theory},
  year={2018}
}
Conditional independence, graphical models and sparsity are key notions for parsimonious statistical models and for understanding the structural relationships in the data. The theory of multivariate and spatial extremes describes the risk of rare events through asymptotically justified limit models such as max-stable and multivariate Pareto distributions. Statistical modelling in this field has been limited to moderate dimensions so far, partly owing to complicated likelihoods and a lack of… Expand
21 Citations

Figures from this paper

Advances in Statistical Modeling of Spatial Extremes
  • 4
  • PDF
Conditional Independence in Max-linear Bayesian Networks
  • 5
  • PDF
Fe b 20 20 CONDITIONAL INDEPENDENCE IN MAX-LINEAR BAYESIAN NETWORKS
Inference on extremal dependence in a latent Markov tree model attracted to a H\"usler-Reiss distribution
  • 3
  • Highly Influenced
Bayesian Spatial Clustering of Extremal Behavior for Hydrological Variables
  • 1
  • PDF
Recursive max-linear models with propagating noise
  • 5
  • PDF
Informative Clusters for Multivariate Extremes
Higher-dimensional spatial extremes via single-site conditioning
  • 14
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 149 REFERENCES
Graphical Models, Exponential Families, and Variational Inference
  • 3,405
  • PDF
Self-consistent estimation of conditional multivariate extreme value distributions
  • Ye Liu, J. Tawn
  • Computer Science, Mathematics
  • J. Multivar. Anal.
  • 2014
  • 9
Multivariate peaks over thresholds models
  • 33
  • PDF
Structure Learning in Graphical Modeling
  • 113
  • PDF
...
1
2
3
4
5
...