Approximate Bayesian computing for spatial extremes

DOI10.1016/J.CSDA.2011.12.003zbMATH Open1246.65023arXiv1109.4166OpenAlexW2080144446MaRDI QIDQ434906FDOQ434906

Authors: Robert J. Erhardt, Richard L. Smith 

Publication date: 16 July 2012

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Abstract: Statistical analysis of max-stable processes used to model spatial extremes has been limited by the difficulty in calculating the joint likelihood function. This precludes all standard likelihood-based approaches, including Bayesian approaches. In this paper we present a Bayesian approach through the use of approximate Bayesian computing. This circumvents the need for a joint likelihood function by instead relying on simulations from the (unavailable) likelihood. This method is compared with an alternative approach based on the composite likelihood. We demonstrate that approximate Bayesian computing can result in a lower mean square error than the composite likelihood approach when estimating the spatial dependence of extremes, though at an appreciably higher computational cost. We also illustrate the performance of the method with an application to US temperature data to estimate the risk of crop loss due to an unlikely freeze event.

Full work available at URL: https://arxiv.org/abs/1109.4166

Recommendations

• Modelling extremes using approximate Bayesian computation
• Approximate Bayesian computation with composite score functions
• ABC model selection for spatial extremes models applied to south Australian maximum temperature data
• Likelihood-based inference for max-stable processes
• Bayesian inference for multivariate extreme value distributions

zbMATH Keywords

composite likelihoodnumerical examplesextremal coefficientmean square errorspatial extremesmax-stable processapproximate Bayesian computinglikelihood-freeunlikely freeze eventUS temperature data

Mathematics Subject Classification ID

Applications of statistics to environmental and related topics (62P12) Bayesian problems; characterization of Bayes procedures (62C10) Computational methods for problems pertaining to geophysics (86-08) Meteorology and atmospheric physics (86A10)

Cites Work

• An introduction to statistical modeling of extreme values
• A note on composite likelihood inference and model selection
• Title not available (Why is that?)
• Title not available (Why is that?)
• Likelihood-based inference for max-stable processes
• Extreme value theory. An introduction.
• Stationary max-stable fields associated to negative definite functions
• Extremes and related properties of random sequences and processes
• A spectral representation for max-stable processes
• Models for stationary max-stable random fields
• On the likelihood function of Gaussian max-stable processes
• Variograms for spatial max-stable random fields
• Title not available (Why is that?)
• Title not available (Why is that?)
• Approximate Bayesian computation: a nonparametric perspective
• Inference for Stereological Extremes
• Spatial modeling of extreme snow depth
• Adaptive approximate Bayesian computation
• Heavy-Tail Phenomena
• Dependence measures for extreme value analyses
• Extreme values of independent stochastic processes

Cited In (14)

• Bayesian estimation of locations of lightning events
• Bayesian inference from composite likelihoods, with an application to spatial extremes
• An approximate likelihood perspective on ABC methods
• A Bayesian hierarchical model for spatial extremes with multiple durations
• Lazy ABC
• Weather derivative risk measures for extreme events
• Bayesian Spatial Clustering of Extremal Behavior for Hydrological Variables
• Neural networks for parameter estimation in intractable models
• ABC model selection for spatial extremes models applied to south Australian maximum temperature data
• CRPS M-estimation for max-stable models
• Modelling extremes using approximate Bayesian computation
• Practical Bayesian modeling and inference for massive spatial data sets on modest computing environments^†
• Simulation-based Bayesian inference for epidemic models
• Approximate Bayesian computation with composite score functions

Uses Software

• ismev

This page was built for publication: Approximate Bayesian computing for spatial extremes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q434906)