Discretization error for the maximum of a Gaussian field

被引：3

作者：

Azais, Jean-Marc ^{[1
]}

Chassan, Malika ^{[1
]}

机构：

[1] Univ Paul Sabatier, Inst Math Toulouse, UMR 5219, 118 Route Narbonne, F-31062 Toulouse 9, France

来源：

STOCHASTIC PROCESSES AND THEIR APPLICATIONS | 2020年 / 130卷 / 02期

关键词：

Gaussian field; Field maximum; Discretization error; Slepian model; LOCATION;

D O I：

10.1016/j.spa.2019.02.002

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：

The paper considers the difference between (a) the true maximum of a Gaussian field on a square and (b) its maximum on a regular grid. This difference is called the discretization error. A kind of Slepian model is used to study the behavior of the field around the location of the maximum. We show that the normalized discretization error can be bounded by a quantity that converges to a uniform variable, depending on the Hessian matrix at the point of the maximum. The bound is applied to simulated and real data (satellite positioning data). (C) 2019 Elsevier B.V. All rights reserved.

引用

页码：545 / 559

页数：15

共 18 条

[1]

Adler R. J., 2004, RANDOM FIELDS GEOMET

[2]

[Anonymous], 2015, STAT SPATIAL DATA

[3]

[Anonymous], 2000, WAFO MATL TOOLB AN R

[4]

Azais J.-M., 2009, Level Sets and Extrema of Random Processes and Fields

[5]

Brodtkorb PA, 2000, INT OFFSHORE POLAR E, P343

[6]

Chassan M, 2015, I NAVIG SAT DIV INT, P3599

[7]

Husler J., 2004, EXTREMES, V7, P179

[8]

Leadbetter M., 1983, Extremes and related properties of random sequences and processes

[9] ON THE ABSOLUTE CONTINUITY OF DISTRIBUTIONS OF FUNCTIONALS OF RANDOM-PROCESSES [J].

LIFSHITS, MA .

THEORY OF PROBABILITY AND ITS APPLICATIONS, 1983, 27 (03) :600-607

[10]

Pimentel LPR, 2014, J APPL PROBAB, V51, P152

← 1 2 →