Hierarchical space-time modeling of asymptotically independent exceedances with an application to precipitation data
From MaRDI portal
Publication:5130596
DOI10.1080/01621459.2019.1617152zbMATH Open1445.62250arXiv1708.02447OpenAlexW2946511436WikidataQ127880412 ScholiaQ127880412MaRDI QIDQ5130596FDOQ5130596
Authors: Jean-Noel Bacro, Carlo Gaetan, Gwladys Toulemonde, T. Opitz 
Publication date: 28 October 2020
Published in: Journal of the American Statistical Association (Search for Journal in Brave)
Abstract: The statistical modeling of space-time extremes in environmental applications is key to understanding complex dependence structures in original event data and to generating realistic scenarios for impact models. In this context of high-dimensional data, we propose a novel hierarchical model for high threshold exceedances defined over continuous space and time by embedding a space-time Gamma process convolution for the rate of an exponential variable, leading to asymptotic independence in space and time. Its physically motivated anisotropic dependence structure is based on geometric objects moving through space-time according to a velocity vector. We demonstrate that inference based on weighted pairwise likelihood is fast and accurate. The usefulness of our model is illustrated by an application to hourly precipitation data from a study region in Southern France, where it clearly improves on an alternative censored Gaussian space-time random field model. While classical limit models based on threshold-stability fail to appropriately capture relatively fast joint tail decay rates between asymptotic dependence and classical independence, strong empirical evidence from our application and other recent case studies motivates the use of more realistic asymptotic independence models such as ours.
Full work available at URL: https://arxiv.org/abs/1708.02447
Recommendations
composite likelihoodasymptotic independencegamma random fieldshourly precipitationspacetime convolutionspacetime extremes
Inference from spatial processes (62M30) Random fields; image analysis (62M40) Statistics of extreme values; tail inference (62G32) Applications of statistics to environmental and related topics (62P12)
Cites Work
- A hierarchical max-stable spatial model for extreme precipitation
- Computation of multivariate normal and \(t\) probabilities
- A note on composite likelihood inference and model selection
- Title not available (Why is that?)
- Estimating space and space-time covariance functions for large data sets: a weighted composite likelihood approach
- Extreme value theory. An introduction.
- Stationary max-stable fields associated to negative definite functions
- Models for stationary max-stable random fields
- A Bayesian analysis of some nonparametric problems
- Bayesian Spatial Modeling of Extreme Precipitation Return Levels
- The Stationary Bootstrap
- Bivariate extreme statistics. I
- Efficient inference and simulation for elliptical Pareto processes
- Extremal \(t\) processes: elliptical domain of attraction and a spectral representation
- Space–Time Modelling of Extreme Events
- Statistical modeling of spatial extremes
- Integer-valued trawl processes: a class of stationary infinitely divisible processes
- Poisson/gamma random field models for spatial statistics
- Some models for rainfall based on stochastic point processes
- The use of subseries values for estimating the variance of a general statistic from a stationary sequence
- Spatial regression models for extremes
- A hierarchical model for the analysis of spatial rainfall extremes
- A flexible dependence model for spatial extremes
- Dependence modelling for spatial extremes
- Max-stable processes for modeling extremes observed in space and time
- The generalized Pareto process; with a view towards application and simulation
- Geostatistics of dependent and asymptotically independent extremes
- Modeling Spatial Processes with Unknown Extremal Dependence Class
- Geostatistics of extremes
- Dependence measures for extreme value analyses
- The Multivariate Gaussian Tail Model: An Application to Oceanographic Data
- Title not available (Why is that?)
- Extreme value theory for space-time processes with heavy-tailed distributions
- Calculating ellipse overlap areas
- A latent process model for temporal extremes
- Latent process modelling of threshold exceedances in hourly rainfall series
- Statistical Inference for Max-Stable Processes in Space and Time
- Practical nonparametric and semiparametric Bayesian statistics
- A Space-Time Skew-t Model for Threshold Exceedances
- The spectrogram: a threshold-based inferential tool for extremes of stochastic processes
Cited In (12)
- Advances in statistical modeling of spatial extremes
- A modeler's guide to extreme value software
- Statistical analysis and modeling of precipitation data
- Limit theorems for trawl processes
- Spatio-temporal prediction of missing temperature with stochastic Poisson equations. The LC2019 team winning entry for the EVA 2019 data competition
- Periodic trawl processes: simulation, statistical inference and applications in energy markets
- A hierarchical model for the analysis of spatial rainfall extremes
- A parametric model for distributions with flexible behavior in both tails
- Spatial hierarchical modeling of threshold exceedances using rate mixtures
- Semiparametric estimation for space-time max-stable processes: an \(F\)-madogram-based approach
- Partial Tail-Correlation Coefficient Applied to Extremal-Network Learning
- A Space-Time Skew-t Model for Threshold Exceedances
This page was built for publication: Hierarchical space-time modeling of asymptotically independent exceedances with an application to precipitation data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5130596)
