Conditionally Max-stable Random Fields based on log Gaussian Cox Processes

TL;DR

This paper introduces a new class of spatial stochastic processes based on Cox processes that are max-stable and exhibit short-range dependence, with feasible statistical inference methods.

Contribution

It presents a novel class of max-stable random fields derived from log Gaussian Cox processes, expanding modeling options for spatial extremes.

Findings

Models have short-range dependence

Statistical inference is feasible under certain conditions

The class is within the max-domain of attraction of known max-stable processes

Abstract

We introduce a class of spatial stochastic processes in the max-domain of attraction of familiar max-stable processes. The new class is based on Cox processes and comprises models with short range dependence. We show that statistical inference is possible within the given framework, at least under some reasonable restrictions.