Sampling sup-normalized spectral functions for Brown-Resnick processes

被引:1
作者
Oesting, Marco [1 ]
Schlather, Martin [2 ]
Schillings, Claudia [2 ]
机构
[1] Univ Siegen, Dept Math, Walter Flex Str 3, D-57072 Siegen, Germany
[2] Univ Mannheim, Inst Math, Mannheim, Germany
关键词
Markov chain Monte Carlo; max-stable process; Pareto process; rejection sampling; spatial extremes; SIMULATION; PEAKS;
D O I
10.1002/sta4.228
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Sup-normalized spectral functions form building blocks of max-stable and Pareto processes and therefore play an important role in modelling spatial extremes. For one of the most popular examples, the Brown-Resnick process, simulation is not straightforward. In this paper, we generalize two approaches for simulation via Markov chain Monte Carlo methods and rejection sampling by introducing new classes of proposal densities. In both cases, we provide an optimal choice of the proposal density with respect to sampling efficiency. The performance of the procedures is demonstrated in an example.
引用
收藏
页数:11
相关论文
共 17 条
[1]  
[Anonymous], 2006, SPRING S OPERAT RES, DOI 10.1007/0-387-34471-3
[2]  
Cressie NAC., 1993, Statistics for spatial data, DOI [10.1002/9781119115151, DOI 10.1002/9781119115151, DOI 10.1002/9781119115151.CH1]
[3]   High-dimensional peaks-over-threshold inference [J].
de Fondeville, R. ;
Davison, A. C. .
BIOMETRIKA, 2018, 105 (03) :575-592
[4]  
DEHAAN L, 1984, ANN PROBAB, V12, P1194
[5]  
Devroye L., 1986, Non-Uniform Random Variate Generation
[6]   Exact simulation of Brown-Resnick random fields at a finite number of locations [J].
Dieker, A. B. ;
Mikosch, T. .
EXTREMES, 2015, 18 (02) :301-314
[7]   Exact simulation of max-stable processes [J].
Dombry, Clement ;
Engelke, Sebastian ;
Oesting, Marco .
BIOMETRIKA, 2016, 103 (02) :303-317
[8]   Functional regular variations, Pareto processes and peaks over threshold [J].
Dombry, Clement ;
Ribatet, Mathieu .
STATISTICS AND ITS INTERFACE, 2015, 8 (01) :9-17
[9]   The generalized Pareto process; with a view towards application and simulation [J].
Ferreira, Ana ;
De Haan, Laurens .
BERNOULLI, 2014, 20 (04) :1717-1737
[10]   A NUMERICALLY STABLE DUAL METHOD FOR SOLVING STRICTLY CONVEX QUADRATIC PROGRAMS [J].
GOLDFARB, D ;
IDNANI, A .
MATHEMATICAL PROGRAMMING, 1983, 27 (01) :1-33