Dynamic spatio-temporal models for spatial data

Trevor J. Hefley, Mevin B. Hooten, Ephraim Mont Hanks, Robin E. Russell, Daniel P. Walsh

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Analyzing spatial data often requires modeling dependencies created by a dynamic spatio-temporal data generating process. In many applications, a generalized linear mixed model (GLMM) is used with a random effect to account for spatial dependence and to provide optimal spatial predictions. Location-specific covariates are often included as fixed effects in a GLMM and may be collinear with the spatial random effect, which can negatively affect inference. We propose a dynamic approach to account for spatial dependence that incorporates scientific knowledge of the spatio-temporal data generating process. Our approach relies on a dynamic spatio-temporal model that explicitly incorporates location-specific covariates. We illustrate our approach with a spatially varying ecological diffusion model implemented using a computationally efficient homogenization technique. We apply our model to understand individual-level and location-specific risk factors associated with chronic wasting disease in white-tailed deer from Wisconsin, USA and estimate the location the disease was first introduced. We compare our approach to several existing methods that are commonly used in spatial statistics. Our spatio-temporal approach resulted in a higher predictive accuracy when compared to methods based on optimal spatial prediction, obviated confounding among the spatially indexed covariates and the spatial random effect, and provided additional information that will be important for containing disease outbreaks.

Original languageEnglish (US)
Pages (from-to)206-220
Number of pages15
JournalSpatial Statistics
Volume20
DOIs
StatePublished - May 1 2017

Fingerprint

Spatio-temporal Model
Spatial Data
spatial data
Dynamic Model
Random Effects
Optimal Prediction
Spatial Prediction
Covariates
Spatio-temporal Data
Generalized Linear Mixed Model
Spatial Dependence
Spatial Statistics
Ecological Model
Chronic Disease
chronic wasting disease
Fixed Effects
Confounding
Collinear
Diffusion Model
Risk Factors

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Computers in Earth Sciences
  • Management, Monitoring, Policy and Law

Cite this

Hefley, T. J., Hooten, M. B., Hanks, E. M., Russell, R. E., & Walsh, D. P. (2017). Dynamic spatio-temporal models for spatial data. Spatial Statistics, 20, 206-220. https://doi.org/10.1016/j.spasta.2017.02.005
Hefley, Trevor J. ; Hooten, Mevin B. ; Hanks, Ephraim Mont ; Russell, Robin E. ; Walsh, Daniel P. / Dynamic spatio-temporal models for spatial data. In: Spatial Statistics. 2017 ; Vol. 20. pp. 206-220.
@article{0f2e25736a564afdb6282a55ae74a6b9,
title = "Dynamic spatio-temporal models for spatial data",
abstract = "Analyzing spatial data often requires modeling dependencies created by a dynamic spatio-temporal data generating process. In many applications, a generalized linear mixed model (GLMM) is used with a random effect to account for spatial dependence and to provide optimal spatial predictions. Location-specific covariates are often included as fixed effects in a GLMM and may be collinear with the spatial random effect, which can negatively affect inference. We propose a dynamic approach to account for spatial dependence that incorporates scientific knowledge of the spatio-temporal data generating process. Our approach relies on a dynamic spatio-temporal model that explicitly incorporates location-specific covariates. We illustrate our approach with a spatially varying ecological diffusion model implemented using a computationally efficient homogenization technique. We apply our model to understand individual-level and location-specific risk factors associated with chronic wasting disease in white-tailed deer from Wisconsin, USA and estimate the location the disease was first introduced. We compare our approach to several existing methods that are commonly used in spatial statistics. Our spatio-temporal approach resulted in a higher predictive accuracy when compared to methods based on optimal spatial prediction, obviated confounding among the spatially indexed covariates and the spatial random effect, and provided additional information that will be important for containing disease outbreaks.",
author = "Hefley, {Trevor J.} and Hooten, {Mevin B.} and Hanks, {Ephraim Mont} and Russell, {Robin E.} and Walsh, {Daniel P.}",
year = "2017",
month = "5",
day = "1",
doi = "10.1016/j.spasta.2017.02.005",
language = "English (US)",
volume = "20",
pages = "206--220",
journal = "Spatial Statistics",
issn = "2211-6753",
publisher = "Elsevier BV",

}

Hefley, TJ, Hooten, MB, Hanks, EM, Russell, RE & Walsh, DP 2017, 'Dynamic spatio-temporal models for spatial data', Spatial Statistics, vol. 20, pp. 206-220. https://doi.org/10.1016/j.spasta.2017.02.005

Dynamic spatio-temporal models for spatial data. / Hefley, Trevor J.; Hooten, Mevin B.; Hanks, Ephraim Mont; Russell, Robin E.; Walsh, Daniel P.

In: Spatial Statistics, Vol. 20, 01.05.2017, p. 206-220.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Dynamic spatio-temporal models for spatial data

AU - Hefley, Trevor J.

AU - Hooten, Mevin B.

AU - Hanks, Ephraim Mont

AU - Russell, Robin E.

AU - Walsh, Daniel P.

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Analyzing spatial data often requires modeling dependencies created by a dynamic spatio-temporal data generating process. In many applications, a generalized linear mixed model (GLMM) is used with a random effect to account for spatial dependence and to provide optimal spatial predictions. Location-specific covariates are often included as fixed effects in a GLMM and may be collinear with the spatial random effect, which can negatively affect inference. We propose a dynamic approach to account for spatial dependence that incorporates scientific knowledge of the spatio-temporal data generating process. Our approach relies on a dynamic spatio-temporal model that explicitly incorporates location-specific covariates. We illustrate our approach with a spatially varying ecological diffusion model implemented using a computationally efficient homogenization technique. We apply our model to understand individual-level and location-specific risk factors associated with chronic wasting disease in white-tailed deer from Wisconsin, USA and estimate the location the disease was first introduced. We compare our approach to several existing methods that are commonly used in spatial statistics. Our spatio-temporal approach resulted in a higher predictive accuracy when compared to methods based on optimal spatial prediction, obviated confounding among the spatially indexed covariates and the spatial random effect, and provided additional information that will be important for containing disease outbreaks.

AB - Analyzing spatial data often requires modeling dependencies created by a dynamic spatio-temporal data generating process. In many applications, a generalized linear mixed model (GLMM) is used with a random effect to account for spatial dependence and to provide optimal spatial predictions. Location-specific covariates are often included as fixed effects in a GLMM and may be collinear with the spatial random effect, which can negatively affect inference. We propose a dynamic approach to account for spatial dependence that incorporates scientific knowledge of the spatio-temporal data generating process. Our approach relies on a dynamic spatio-temporal model that explicitly incorporates location-specific covariates. We illustrate our approach with a spatially varying ecological diffusion model implemented using a computationally efficient homogenization technique. We apply our model to understand individual-level and location-specific risk factors associated with chronic wasting disease in white-tailed deer from Wisconsin, USA and estimate the location the disease was first introduced. We compare our approach to several existing methods that are commonly used in spatial statistics. Our spatio-temporal approach resulted in a higher predictive accuracy when compared to methods based on optimal spatial prediction, obviated confounding among the spatially indexed covariates and the spatial random effect, and provided additional information that will be important for containing disease outbreaks.

UR - http://www.scopus.com/inward/record.url?scp=85017746789&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017746789&partnerID=8YFLogxK

U2 - 10.1016/j.spasta.2017.02.005

DO - 10.1016/j.spasta.2017.02.005

M3 - Article

AN - SCOPUS:85017746789

VL - 20

SP - 206

EP - 220

JO - Spatial Statistics

JF - Spatial Statistics

SN - 2211-6753

ER -