On edge correction of conditional and intrinsic autoregressions

D. Mondal

doi:10.1093/biomet/asy014

On edge correction of conditional and intrinsic autoregressions

D. Mondal

Research output: Contribution to journal › Review article › peer-review

5 Scopus citations

Abstract

This paper discusses edge correction for a large class of conditional and intrinsic autoregressions on two-dimensional finite regular arrays. The proposed method includes a novel reparameterization, retains the simple neighbourhood structure, ensures the nonnegative definiteness of the precision matrix, and enables scalable matrix-free statistical computation. The edge correction provides new insight into how higher-order differencing enters into the precision matrix of a conditional autoregression.

Original language	English
Pages (from-to)	447-454
Number of pages	8
Journal	Biometrika
Volume	105
Issue number	2
DOIs	https://doi.org/10.1093/biomet/asy014
State	Published - Jun 1 2018

Keywords

Discrete cosine transform
Gaussian Markov random field
Matrix-free computation
Positive polynomial
Sparse precision matrix
Spatial statistics

Access to Document

10.1093/biomet/asy014

Cite this

@article{5aec572052dd46b599b758ed42f68f10,

title = "On edge correction of conditional and intrinsic autoregressions",

abstract = "This paper discusses edge correction for a large class of conditional and intrinsic autoregressions on two-dimensional finite regular arrays. The proposed method includes a novel reparameterization, retains the simple neighbourhood structure, ensures the nonnegative definiteness of the precision matrix, and enables scalable matrix-free statistical computation. The edge correction provides new insight into how higher-order differencing enters into the precision matrix of a conditional autoregression.",

keywords = "Discrete cosine transform, Gaussian Markov random field, Matrix-free computation, Positive polynomial, Sparse precision matrix, Spatial statistics",

author = "D. Mondal",

note = "Publisher Copyright: {\textcopyright} 2018 Biometrika Trust.",

year = "2018",

month = jun,

day = "1",

doi = "10.1093/biomet/asy014",

language = "English",

volume = "105",

pages = "447--454",

journal = "Biometrika",

issn = "0006-3444",

number = "2",

}

TY - JOUR

T1 - On edge correction of conditional and intrinsic autoregressions

AU - Mondal, D.

PY - 2018/6/1

Y1 - 2018/6/1

N2 - This paper discusses edge correction for a large class of conditional and intrinsic autoregressions on two-dimensional finite regular arrays. The proposed method includes a novel reparameterization, retains the simple neighbourhood structure, ensures the nonnegative definiteness of the precision matrix, and enables scalable matrix-free statistical computation. The edge correction provides new insight into how higher-order differencing enters into the precision matrix of a conditional autoregression.

AB - This paper discusses edge correction for a large class of conditional and intrinsic autoregressions on two-dimensional finite regular arrays. The proposed method includes a novel reparameterization, retains the simple neighbourhood structure, ensures the nonnegative definiteness of the precision matrix, and enables scalable matrix-free statistical computation. The edge correction provides new insight into how higher-order differencing enters into the precision matrix of a conditional autoregression.

KW - Discrete cosine transform

KW - Gaussian Markov random field

KW - Matrix-free computation

KW - Positive polynomial

KW - Sparse precision matrix

KW - Spatial statistics

UR - https://www.scopus.com/pages/publications/85048691365

U2 - 10.1093/biomet/asy014

DO - 10.1093/biomet/asy014

M3 - Review article

AN - SCOPUS:85048691365

SN - 0006-3444

VL - 105

SP - 447

EP - 454

JO - Biometrika

JF - Biometrika

IS - 2

ER -

On edge correction of conditional and intrinsic autoregressions

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this