The University of Southampton
University of Southampton Institutional Repository

Efficient Bayesian hierarchical small area population estimation using INLA-SPDE: integrating multiple data sources and spatial-autocorrelation

Efficient Bayesian hierarchical small area population estimation using INLA-SPDE: integrating multiple data sources and spatial-autocorrelation
Efficient Bayesian hierarchical small area population estimation using INLA-SPDE: integrating multiple data sources and spatial-autocorrelation
Statistical modelling approaches which produce fine spatial resolution population estimates have been developed to fill data gaps in resource-poor countries where census data are either outdated or incomplete. These population modelling methods often draw upon recent georeferenced sample population enumeration datasets to predict population density and distribution at both sampled and non-sampled locations, based on their correlation with a set of carefully selected geospatial covariates. These modelled population estimates are increasingly used to support governance, health surveillance, equitable resource allocation, and humanitarian response. However, methodological challenges remain. For example, the georeferenced sample enumeration data are usually disparate and patchy in their distributions, with a high proportion of non-sampled locations that result in highly uncertain estimates. Here, we present a model-based Bayesian geostatistical small area population estimation approach which simultaneously · Combines multiple sample population enumeration datasets and· Explicitly integrates spatial autocorrelation within a single modelling framework. Findings from a simulation study show varying levels of accuracy in the posterior parameter estimates over different levels of spatial variance and data missingness. The methodology, which was further validated using five nationally representative household listing datasets in Cameroon, provides a valuable methodological development in small area population estimation modelling from sparsely distributed sample enumeration data.
Preprints.Org
Nnanatu, Chibuzor Christopher
24be7c1b-a677-4086-91b4-a9d9b1efa5a3
Yankey, Ortis
9965d053-8afb-462f-b7fe-b270e21f2ec1
Dzossa, Anaclet D.
32b9b918-3113-4cb5-8c25-2c801b3cb5df
Abbott, Thomas
8b1d4865-a634-4b8a-a39a-ff8842709edd
Gadiaga, Assane
eada3464-b0a2-4aaa-b594-eff8182c2aee
Lazar, Attila
d7f835e7-1e3d-4742-b366-af19cf5fc881
Tatem, Andrew
6c6de104-a5f9-46e0-bb93-a1a7c980513e
Nnanatu, Chibuzor Christopher
24be7c1b-a677-4086-91b4-a9d9b1efa5a3
Yankey, Ortis
9965d053-8afb-462f-b7fe-b270e21f2ec1
Dzossa, Anaclet D.
32b9b918-3113-4cb5-8c25-2c801b3cb5df
Abbott, Thomas
8b1d4865-a634-4b8a-a39a-ff8842709edd
Gadiaga, Assane
eada3464-b0a2-4aaa-b594-eff8182c2aee
Lazar, Attila
d7f835e7-1e3d-4742-b366-af19cf5fc881
Tatem, Andrew
6c6de104-a5f9-46e0-bb93-a1a7c980513e

[Unknown type: UNSPECIFIED]

Record type: UNSPECIFIED

Abstract

Statistical modelling approaches which produce fine spatial resolution population estimates have been developed to fill data gaps in resource-poor countries where census data are either outdated or incomplete. These population modelling methods often draw upon recent georeferenced sample population enumeration datasets to predict population density and distribution at both sampled and non-sampled locations, based on their correlation with a set of carefully selected geospatial covariates. These modelled population estimates are increasingly used to support governance, health surveillance, equitable resource allocation, and humanitarian response. However, methodological challenges remain. For example, the georeferenced sample enumeration data are usually disparate and patchy in their distributions, with a high proportion of non-sampled locations that result in highly uncertain estimates. Here, we present a model-based Bayesian geostatistical small area population estimation approach which simultaneously · Combines multiple sample population enumeration datasets and· Explicitly integrates spatial autocorrelation within a single modelling framework. Findings from a simulation study show varying levels of accuracy in the posterior parameter estimates over different levels of spatial variance and data missingness. The methodology, which was further validated using five nationally representative household listing datasets in Cameroon, provides a valuable methodological development in small area population estimation modelling from sparsely distributed sample enumeration data.

Text
preprints202501.0588.v1 - Author's Original
Available under License Creative Commons Attribution.
Download (2MB)

More information

Published date: 8 January 2025

Identifiers

Local EPrints ID: 497946
URI: http://eprints.soton.ac.uk/id/eprint/497946
PURE UUID: a9c9d47e-37c0-40b8-828f-753636ad11c5
ORCID for Chibuzor Christopher Nnanatu: ORCID iD orcid.org/0000-0002-5841-3700
ORCID for Ortis Yankey: ORCID iD orcid.org/0000-0002-0808-884X
ORCID for Attila Lazar: ORCID iD orcid.org/0000-0003-2033-2013
ORCID for Andrew Tatem: ORCID iD orcid.org/0000-0002-7270-941X

Catalogue record

Date deposited: 05 Feb 2025 17:32
Last modified: 22 Aug 2025 02:34

Export record

Altmetrics

Contributors

Author: Chibuzor Christopher Nnanatu ORCID iD
Author: Ortis Yankey ORCID iD
Author: Anaclet D. Dzossa
Author: Thomas Abbott
Author: Assane Gadiaga
Author: Attila Lazar ORCID iD
Author: Andrew Tatem ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×