Bayesian Inference For The Brown-Resnick Process, With An Application To Extreme Low Temperatures
The Brown-Resnick max-stable process has proven to be well suited for modeling extremes of complex environmental processes, but in many applications its likelihood function is intractable and inference must be based on a composite likelihood, thereby preventing the use of classical Bayesian techniqu...
Published in: | The Annals of Applied Statistics |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | unknown |
Published: |
Cleveland, Inst Mathematical Statistics
2017
|
Subjects: | |
Online Access: | https://doi.org/10.1214/16-Aoas980 http://infoscience.epfl.ch/record/227038 |
id |
ftinfoscience:oai:infoscience.tind.io:227038 |
---|---|
record_format |
openpolar |
spelling |
ftinfoscience:oai:infoscience.tind.io:227038 2023-05-15T16:11:48+02:00 Bayesian Inference For The Brown-Resnick Process, With An Application To Extreme Low Temperatures Thibaud, Emeric Aalto, Juha Cooley, Daniel S. Davison, Anthony C. Heikkinen, Juha 2017-03-27T16:09:06Z https://doi.org/10.1214/16-Aoas980 http://infoscience.epfl.ch/record/227038 unknown Cleveland, Inst Mathematical Statistics doi:10.1214/16-Aoas980 ISI:000392819100027 http://infoscience.epfl.ch/record/227038 http://infoscience.epfl.ch/record/227038 Text 2017 ftinfoscience https://doi.org/10.1214/16-Aoas980 2023-02-13T22:39:23Z The Brown-Resnick max-stable process has proven to be well suited for modeling extremes of complex environmental processes, but in many applications its likelihood function is intractable and inference must be based on a composite likelihood, thereby preventing the use of classical Bayesian techniques. In this paper we exploit a case in which the full likelihood of a Brown-Resnick process can be calculated, using componentwise maxima and their partitions in terms of individual events, and we propose two new approaches to inference. The first estimates the partitions using declustering, while the second uses random partitions in a Markov chain Monte Carlo algorithm. We use these approaches to construct a Bayesian hierarchical model for extreme low temperatures in northern Fennoscandia. Text Fennoscandia EPFL Infoscience (Ecole Polytechnique Fédérale Lausanne) The Annals of Applied Statistics 10 4 |
institution |
Open Polar |
collection |
EPFL Infoscience (Ecole Polytechnique Fédérale Lausanne) |
op_collection_id |
ftinfoscience |
language |
unknown |
description |
The Brown-Resnick max-stable process has proven to be well suited for modeling extremes of complex environmental processes, but in many applications its likelihood function is intractable and inference must be based on a composite likelihood, thereby preventing the use of classical Bayesian techniques. In this paper we exploit a case in which the full likelihood of a Brown-Resnick process can be calculated, using componentwise maxima and their partitions in terms of individual events, and we propose two new approaches to inference. The first estimates the partitions using declustering, while the second uses random partitions in a Markov chain Monte Carlo algorithm. We use these approaches to construct a Bayesian hierarchical model for extreme low temperatures in northern Fennoscandia. |
format |
Text |
author |
Thibaud, Emeric Aalto, Juha Cooley, Daniel S. Davison, Anthony C. Heikkinen, Juha |
spellingShingle |
Thibaud, Emeric Aalto, Juha Cooley, Daniel S. Davison, Anthony C. Heikkinen, Juha Bayesian Inference For The Brown-Resnick Process, With An Application To Extreme Low Temperatures |
author_facet |
Thibaud, Emeric Aalto, Juha Cooley, Daniel S. Davison, Anthony C. Heikkinen, Juha |
author_sort |
Thibaud, Emeric |
title |
Bayesian Inference For The Brown-Resnick Process, With An Application To Extreme Low Temperatures |
title_short |
Bayesian Inference For The Brown-Resnick Process, With An Application To Extreme Low Temperatures |
title_full |
Bayesian Inference For The Brown-Resnick Process, With An Application To Extreme Low Temperatures |
title_fullStr |
Bayesian Inference For The Brown-Resnick Process, With An Application To Extreme Low Temperatures |
title_full_unstemmed |
Bayesian Inference For The Brown-Resnick Process, With An Application To Extreme Low Temperatures |
title_sort |
bayesian inference for the brown-resnick process, with an application to extreme low temperatures |
publisher |
Cleveland, Inst Mathematical Statistics |
publishDate |
2017 |
url |
https://doi.org/10.1214/16-Aoas980 http://infoscience.epfl.ch/record/227038 |
genre |
Fennoscandia |
genre_facet |
Fennoscandia |
op_source |
http://infoscience.epfl.ch/record/227038 |
op_relation |
doi:10.1214/16-Aoas980 ISI:000392819100027 http://infoscience.epfl.ch/record/227038 |
op_doi |
https://doi.org/10.1214/16-Aoas980 |
container_title |
The Annals of Applied Statistics |
container_volume |
10 |
container_issue |
4 |
_version_ |
1765996991476662272 |