Model-Based Geostatistics for Prevalence Mapping in Low-Resource Settings

Peter J. Diggle, Emanuele Giorgi

Research output: Contribution to journalArticle

Abstract

In low-resource settings, prevalence mapping relies on empirical prevalence data from a finite, often spatially sparse, set of surveys of communities within the region of interest, possibly supplemented by remotely sensed images that can act as proxies for environmental risk factors. A standard geostatistical model for data of this kind is a generalized linear mixed model with binomial error distribution, logistic link, and a combination of explanatory variables and a Gaussian spatial stochastic process in the linear predictor. In this article, we first review statistical methods and software associated with this standard model, then consider several methodological extensions whose development has been motivated by the requirements of specific applications. These include: methods for combining randomized survey data with data from nonrandomized, and therefore potentially biased, surveys; spatio-temporal extensions; and spatially structured zero-inflation. Throughout, we illustrate the methods with disease mapping applications that have arisen through our involvement with a range of African public health programs.

Original languageEnglish (US)
Pages (from-to)1096-1120
Number of pages25
JournalJournal of the American Statistical Association
Volume111
Issue number515
DOIs
StatePublished - Jul 2 2016
Externally publishedYes

Fingerprint

Geostatistics
Model-based
Resources
Standard Model
Zero-inflation
Disease Mapping
Logistics/distribution
Generalized Linear Mixed Model
Statistical Software
Spatial Process
Environmental Factors
Survey Data
Public Health
Risk Factors
Region of Interest
Statistical method
Biased
Stochastic Processes
Predictors
Requirements

Keywords

  • Geostatistics
  • Multiple surveys
  • Prevalence
  • Spatio-temporal models
  • Zero-inflation

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Model-Based Geostatistics for Prevalence Mapping in Low-Resource Settings. / Diggle, Peter J.; Giorgi, Emanuele.

In: Journal of the American Statistical Association, Vol. 111, No. 515, 02.07.2016, p. 1096-1120.

Research output: Contribution to journalArticle

Diggle, Peter J. ; Giorgi, Emanuele. / Model-Based Geostatistics for Prevalence Mapping in Low-Resource Settings. In: Journal of the American Statistical Association. 2016 ; Vol. 111, No. 515. pp. 1096-1120.
@article{690fc0f601d2431592fadcc2ba4836bf,
title = "Model-Based Geostatistics for Prevalence Mapping in Low-Resource Settings",
abstract = "In low-resource settings, prevalence mapping relies on empirical prevalence data from a finite, often spatially sparse, set of surveys of communities within the region of interest, possibly supplemented by remotely sensed images that can act as proxies for environmental risk factors. A standard geostatistical model for data of this kind is a generalized linear mixed model with binomial error distribution, logistic link, and a combination of explanatory variables and a Gaussian spatial stochastic process in the linear predictor. In this article, we first review statistical methods and software associated with this standard model, then consider several methodological extensions whose development has been motivated by the requirements of specific applications. These include: methods for combining randomized survey data with data from nonrandomized, and therefore potentially biased, surveys; spatio-temporal extensions; and spatially structured zero-inflation. Throughout, we illustrate the methods with disease mapping applications that have arisen through our involvement with a range of African public health programs.",
keywords = "Geostatistics, Multiple surveys, Prevalence, Spatio-temporal models, Zero-inflation",
author = "Diggle, {Peter J.} and Emanuele Giorgi",
year = "2016",
month = "7",
day = "2",
doi = "10.1080/01621459.2015.1123158",
language = "English (US)",
volume = "111",
pages = "1096--1120",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "515",

}

TY - JOUR

T1 - Model-Based Geostatistics for Prevalence Mapping in Low-Resource Settings

AU - Diggle, Peter J.

AU - Giorgi, Emanuele

PY - 2016/7/2

Y1 - 2016/7/2

N2 - In low-resource settings, prevalence mapping relies on empirical prevalence data from a finite, often spatially sparse, set of surveys of communities within the region of interest, possibly supplemented by remotely sensed images that can act as proxies for environmental risk factors. A standard geostatistical model for data of this kind is a generalized linear mixed model with binomial error distribution, logistic link, and a combination of explanatory variables and a Gaussian spatial stochastic process in the linear predictor. In this article, we first review statistical methods and software associated with this standard model, then consider several methodological extensions whose development has been motivated by the requirements of specific applications. These include: methods for combining randomized survey data with data from nonrandomized, and therefore potentially biased, surveys; spatio-temporal extensions; and spatially structured zero-inflation. Throughout, we illustrate the methods with disease mapping applications that have arisen through our involvement with a range of African public health programs.

AB - In low-resource settings, prevalence mapping relies on empirical prevalence data from a finite, often spatially sparse, set of surveys of communities within the region of interest, possibly supplemented by remotely sensed images that can act as proxies for environmental risk factors. A standard geostatistical model for data of this kind is a generalized linear mixed model with binomial error distribution, logistic link, and a combination of explanatory variables and a Gaussian spatial stochastic process in the linear predictor. In this article, we first review statistical methods and software associated with this standard model, then consider several methodological extensions whose development has been motivated by the requirements of specific applications. These include: methods for combining randomized survey data with data from nonrandomized, and therefore potentially biased, surveys; spatio-temporal extensions; and spatially structured zero-inflation. Throughout, we illustrate the methods with disease mapping applications that have arisen through our involvement with a range of African public health programs.

KW - Geostatistics

KW - Multiple surveys

KW - Prevalence

KW - Spatio-temporal models

KW - Zero-inflation

UR - http://www.scopus.com/inward/record.url?scp=84991671428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991671428&partnerID=8YFLogxK

U2 - 10.1080/01621459.2015.1123158

DO - 10.1080/01621459.2015.1123158

M3 - Article

VL - 111

SP - 1096

EP - 1120

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 515

ER -