Modeling non-stationary processes through dimension expansion

Luke Bornn, Gavin Shaddick, James V Zidek

Research output: Contribution to journalArticle

  • 30 Citations

Abstract

In this paper, we propose a novel approach to modeling nonstationary spatial fields. The proposed method works by expanding the geographic plane over which these processes evolve into higher dimensional spaces, transforming and clarifying complex patterns in the physical plane. By combining aspects of multi-dimensional scaling, group lasso, and latent variable models, a dimensionally sparse projection is found in which the originally nonstationary field exhibits stationarity. Following a comparison with existing methods in a simulated environment, dimension expansion is studied on a classic test-bed data set historically used to study nonstationary models. Following this, we explore the use of dimension expansion in modeling air pollution in the United Kingdom, a process known to be strongly influenced by rural/urban effects, amongst others, which gives rise to a nonstationary field.
LanguageEnglish
Pages281-289
Number of pages9
JournalJournal of the American Statistical Association
Volume107
Issue number497
DOIs
StatusPublished - Mar 2012

Fingerprint

Nonstationary Processes
Modeling
Latent Variable Models
Lasso
Air Pollution
Stationarity
Testbed
High-dimensional
Projection
Scaling
Nonstationary processes

Cite this

Modeling non-stationary processes through dimension expansion. / Bornn, Luke; Shaddick, Gavin; Zidek, James V.

In: Journal of the American Statistical Association, Vol. 107, No. 497, 03.2012, p. 281-289.

Research output: Contribution to journalArticle

@article{50a5909a94cf4fb1a446cb8dcdac0474,
title = "Modeling non-stationary processes through dimension expansion",
abstract = "In this paper, we propose a novel approach to modeling nonstationary spatial fields. The proposed method works by expanding the geographic plane over which these processes evolve into higher dimensional spaces, transforming and clarifying complex patterns in the physical plane. By combining aspects of multi-dimensional scaling, group lasso, and latent variable models, a dimensionally sparse projection is found in which the originally nonstationary field exhibits stationarity. Following a comparison with existing methods in a simulated environment, dimension expansion is studied on a classic test-bed data set historically used to study nonstationary models. Following this, we explore the use of dimension expansion in modeling air pollution in the United Kingdom, a process known to be strongly influenced by rural/urban effects, amongst others, which gives rise to a nonstationary field.",
author = "Luke Bornn and Gavin Shaddick and Zidek, {James V}",
year = "2012",
month = "3",
doi = "10.1080/01621459.2011.646919",
language = "English",
volume = "107",
pages = "281--289",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor & Francis",
number = "497",

}

TY - JOUR

T1 - Modeling non-stationary processes through dimension expansion

AU - Bornn,Luke

AU - Shaddick,Gavin

AU - Zidek,James V

PY - 2012/3

Y1 - 2012/3

N2 - In this paper, we propose a novel approach to modeling nonstationary spatial fields. The proposed method works by expanding the geographic plane over which these processes evolve into higher dimensional spaces, transforming and clarifying complex patterns in the physical plane. By combining aspects of multi-dimensional scaling, group lasso, and latent variable models, a dimensionally sparse projection is found in which the originally nonstationary field exhibits stationarity. Following a comparison with existing methods in a simulated environment, dimension expansion is studied on a classic test-bed data set historically used to study nonstationary models. Following this, we explore the use of dimension expansion in modeling air pollution in the United Kingdom, a process known to be strongly influenced by rural/urban effects, amongst others, which gives rise to a nonstationary field.

AB - In this paper, we propose a novel approach to modeling nonstationary spatial fields. The proposed method works by expanding the geographic plane over which these processes evolve into higher dimensional spaces, transforming and clarifying complex patterns in the physical plane. By combining aspects of multi-dimensional scaling, group lasso, and latent variable models, a dimensionally sparse projection is found in which the originally nonstationary field exhibits stationarity. Following a comparison with existing methods in a simulated environment, dimension expansion is studied on a classic test-bed data set historically used to study nonstationary models. Following this, we explore the use of dimension expansion in modeling air pollution in the United Kingdom, a process known to be strongly influenced by rural/urban effects, amongst others, which gives rise to a nonstationary field.

UR - http://www.scopus.com/inward/record.url?scp=84862848995&partnerID=8YFLogxK

UR - http://dx.doi.org/10.1080/01621459.2011.646919

U2 - 10.1080/01621459.2011.646919

DO - 10.1080/01621459.2011.646919

M3 - Article

VL - 107

SP - 281

EP - 289

JO - Journal of the American Statistical Association

T2 - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 497

ER -