A Bayesian space-time model for discrete spread processes on a lattice

Jed A. Long, Colin Robertson, Farouk S. Nathoo, Trisalyn Nelson

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In this article we present a Bayesian Markov model for investigating environmental spread processes. We formulate a model where the spread of a disease over a heterogeneous landscape through time is represented as a probabilistic function of two processes: local diffusion and random-jump dispersal. This formulation represents two mechanisms of spread which result in highly peaked and long-tailed distributions of dispersal distances (i.e., local and long-distance spread), commonly observed in the spread of infectious diseases and biological invasions. We demonstrate the properties of this model using a simulation experiment and an empirical case study - the spread of mountain pine beetle in western Canada. Posterior predictive checking was used to validate the number of newly inhabited regions in each time period. The model performed well in the simulation study in which a goodness-of-fit statistic measuring the number of newly inhabited regions in each time interval fell within the 95% posterior predictive credible interval in over 97% of simulations. The case study of a mountain pine beetle infestation in western Canada (1999-2009) extended the base model in two ways. First, spatial covariates thought to impact the local diffusion parameters, elevation and forest cover, were included in the model. Second, a refined definition for translocation or jump-dispersal based on mountain pine beetle ecology was incorporated improving the fit of the model. Posterior predictive checks on the mountain pine beetle model found that the observed goodness-of-fit test statistic fell within the 95% posterior predictive credible interval for 8 out of 10. years. The simulation study and case study provide evidence that the model presented here is both robust and flexible; and is therefore appropriate for a wide range of spread processes in epidemiology and ecology.

Original languageEnglish (US)
Pages (from-to)151-162
Number of pages12
JournalSpatial and Spatio-temporal Epidemiology
Volume3
Issue number2
DOIs
StatePublished - Jun 2012
Externally publishedYes

Fingerprint

Space Simulation
Beetles
Ecology
Canada
beetle
simulation
mountain
Communicable Diseases
Epidemiology
ecology
statistics
time
biological invasion
infectious disease
epidemiology
invasion
forest cover
translocation
contagious disease
Disease

Keywords

  • Mountain pine beetle
  • Space-time binary data
  • Spatial random effects
  • Spread process

ASJC Scopus subject areas

  • Epidemiology
  • Infectious Diseases
  • Health, Toxicology and Mutagenesis
  • Geography, Planning and Development

Cite this

A Bayesian space-time model for discrete spread processes on a lattice. / Long, Jed A.; Robertson, Colin; Nathoo, Farouk S.; Nelson, Trisalyn.

In: Spatial and Spatio-temporal Epidemiology, Vol. 3, No. 2, 06.2012, p. 151-162.

Research output: Contribution to journalArticle

Long, Jed A. ; Robertson, Colin ; Nathoo, Farouk S. ; Nelson, Trisalyn. / A Bayesian space-time model for discrete spread processes on a lattice. In: Spatial and Spatio-temporal Epidemiology. 2012 ; Vol. 3, No. 2. pp. 151-162.
@article{9c6999b01a1649a0bb95d6daf7daf241,
title = "A Bayesian space-time model for discrete spread processes on a lattice",
abstract = "In this article we present a Bayesian Markov model for investigating environmental spread processes. We formulate a model where the spread of a disease over a heterogeneous landscape through time is represented as a probabilistic function of two processes: local diffusion and random-jump dispersal. This formulation represents two mechanisms of spread which result in highly peaked and long-tailed distributions of dispersal distances (i.e., local and long-distance spread), commonly observed in the spread of infectious diseases and biological invasions. We demonstrate the properties of this model using a simulation experiment and an empirical case study - the spread of mountain pine beetle in western Canada. Posterior predictive checking was used to validate the number of newly inhabited regions in each time period. The model performed well in the simulation study in which a goodness-of-fit statistic measuring the number of newly inhabited regions in each time interval fell within the 95{\%} posterior predictive credible interval in over 97{\%} of simulations. The case study of a mountain pine beetle infestation in western Canada (1999-2009) extended the base model in two ways. First, spatial covariates thought to impact the local diffusion parameters, elevation and forest cover, were included in the model. Second, a refined definition for translocation or jump-dispersal based on mountain pine beetle ecology was incorporated improving the fit of the model. Posterior predictive checks on the mountain pine beetle model found that the observed goodness-of-fit test statistic fell within the 95{\%} posterior predictive credible interval for 8 out of 10. years. The simulation study and case study provide evidence that the model presented here is both robust and flexible; and is therefore appropriate for a wide range of spread processes in epidemiology and ecology.",
keywords = "Mountain pine beetle, Space-time binary data, Spatial random effects, Spread process",
author = "Long, {Jed A.} and Colin Robertson and Nathoo, {Farouk S.} and Trisalyn Nelson",
year = "2012",
month = "6",
doi = "10.1016/j.sste.2012.04.008",
language = "English (US)",
volume = "3",
pages = "151--162",
journal = "Spatial and Spatio-temporal Epidemiology",
issn = "1877-5845",
publisher = "Elsevier Limited",
number = "2",

}

TY - JOUR

T1 - A Bayesian space-time model for discrete spread processes on a lattice

AU - Long, Jed A.

AU - Robertson, Colin

AU - Nathoo, Farouk S.

AU - Nelson, Trisalyn

PY - 2012/6

Y1 - 2012/6

N2 - In this article we present a Bayesian Markov model for investigating environmental spread processes. We formulate a model where the spread of a disease over a heterogeneous landscape through time is represented as a probabilistic function of two processes: local diffusion and random-jump dispersal. This formulation represents two mechanisms of spread which result in highly peaked and long-tailed distributions of dispersal distances (i.e., local and long-distance spread), commonly observed in the spread of infectious diseases and biological invasions. We demonstrate the properties of this model using a simulation experiment and an empirical case study - the spread of mountain pine beetle in western Canada. Posterior predictive checking was used to validate the number of newly inhabited regions in each time period. The model performed well in the simulation study in which a goodness-of-fit statistic measuring the number of newly inhabited regions in each time interval fell within the 95% posterior predictive credible interval in over 97% of simulations. The case study of a mountain pine beetle infestation in western Canada (1999-2009) extended the base model in two ways. First, spatial covariates thought to impact the local diffusion parameters, elevation and forest cover, were included in the model. Second, a refined definition for translocation or jump-dispersal based on mountain pine beetle ecology was incorporated improving the fit of the model. Posterior predictive checks on the mountain pine beetle model found that the observed goodness-of-fit test statistic fell within the 95% posterior predictive credible interval for 8 out of 10. years. The simulation study and case study provide evidence that the model presented here is both robust and flexible; and is therefore appropriate for a wide range of spread processes in epidemiology and ecology.

AB - In this article we present a Bayesian Markov model for investigating environmental spread processes. We formulate a model where the spread of a disease over a heterogeneous landscape through time is represented as a probabilistic function of two processes: local diffusion and random-jump dispersal. This formulation represents two mechanisms of spread which result in highly peaked and long-tailed distributions of dispersal distances (i.e., local and long-distance spread), commonly observed in the spread of infectious diseases and biological invasions. We demonstrate the properties of this model using a simulation experiment and an empirical case study - the spread of mountain pine beetle in western Canada. Posterior predictive checking was used to validate the number of newly inhabited regions in each time period. The model performed well in the simulation study in which a goodness-of-fit statistic measuring the number of newly inhabited regions in each time interval fell within the 95% posterior predictive credible interval in over 97% of simulations. The case study of a mountain pine beetle infestation in western Canada (1999-2009) extended the base model in two ways. First, spatial covariates thought to impact the local diffusion parameters, elevation and forest cover, were included in the model. Second, a refined definition for translocation or jump-dispersal based on mountain pine beetle ecology was incorporated improving the fit of the model. Posterior predictive checks on the mountain pine beetle model found that the observed goodness-of-fit test statistic fell within the 95% posterior predictive credible interval for 8 out of 10. years. The simulation study and case study provide evidence that the model presented here is both robust and flexible; and is therefore appropriate for a wide range of spread processes in epidemiology and ecology.

KW - Mountain pine beetle

KW - Space-time binary data

KW - Spatial random effects

KW - Spread process

UR - http://www.scopus.com/inward/record.url?scp=84861926682&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861926682&partnerID=8YFLogxK

U2 - 10.1016/j.sste.2012.04.008

DO - 10.1016/j.sste.2012.04.008

M3 - Article

VL - 3

SP - 151

EP - 162

JO - Spatial and Spatio-temporal Epidemiology

JF - Spatial and Spatio-temporal Epidemiology

SN - 1877-5845

IS - 2

ER -