ABC model selection for spatial extremes models applied to South Australian maximum temperature data

TL;DR

This paper explores using approximate Bayesian computation (ABC) for model selection among various max-stable and copula models to analyze South Australian maximum temperature data, addressing the challenge of intractable likelihoods.

Contribution

It introduces an ABC-based approach for model selection in spatial extremes, comparing multiple max-stable and copula models on real temperature data.

Findings

ABC effectively distinguishes between different max-stable models.

The selected models fit the temperature data well.

The approach offers a practical solution for complex spatial extreme models.

Abstract

Max-stable processes are a common choice for modelling spatial extreme data as they arise naturally as the infinite-dimensional generalisation of multivariate extreme value theory. Statistical inference for such models is complicated by the intractability of the multivariate density function. Nonparametric, composite likelihood-based, and Bayesian approaches have been proposed to address this difficulty. More recently, a simulation-based approach using approximate Bayesian computation (ABC) has been employed for estimating parameters of max-stable models. ABC algorithms rely on the evaluation of discrepancies between model simulations and the observed data rather than explicit evaluations of computationally expensive or intractable likelihood functions. The use of an ABC method to perform model selection for max-stable models is explored. Three max-stable models are regarded: the extremal-t model with either a Whittle-Mat\'ern or a powered exponential covariance function, and the Brown-Resnick model with power variogram. In addition, the non-extremal Student-t copula model with a Whittle-Mat\'ern or a powered exponential covariance function is also considered. The method is applied to annual maximum temperature data from 25 weather stations dispersed around South Australia.