Full likelihood inference for max-stable data
Methodology
2018-07-17 v2
Abstract
We show how to perform full likelihood inference for max-stable multivariate distributions or processes based on a stochastic Expectation-Maximisation algorithm, which combines statistical and computational efficiency in high-dimensions. The good performance of this methodology is demonstrated by simulation based on the popular logistic and Brown--Resnick models, and it is shown to provide dramatic computational time improvements with respect to a direct computation of the likelihood. Strategies to further reduce the computational burden are also discussed.
Cite
@article{arxiv.1703.08665,
title = {Full likelihood inference for max-stable data},
author = {Raphaël Huser and Clément Dombry and Mathieu Ribatet and Marc G. Genton},
journal= {arXiv preprint arXiv:1703.08665},
year = {2018}
}