Estimating subnational under-five mortality rates using a spatio-temporal Age-Period-Cohort model

Connor Gascoigne; Theresa Smith; Jon Wakefield; John Paige

doi:10.1016/j.sste.2024.100708

Estimating subnational under-five mortality rates using a spatio-temporal Age-Period-Cohort model

Connor Gascoigne
, Theresa Smith
, Jon Wakefield
, John Paige

Imperial College London
University of Washington
Norwegian National Technical University, (NTNU), Trondheim, Norway

Research output: Contribution to journal › Article › peer-review

3 Citations (SciVal)

Abstract

Subnational estimates of under-five mortality rates (U5MRs) are a vital statistic for the United Nations to reduce mortality inequalities between high-income and Low-and-Middle Income Countries (LMICs). Current methods of modelling U5MR in LMICs smooth across trends in age and year of death, but not birth-cohort, to reduce uncertainty in estimates caused by data-sparsity. Using survey data from Kenya, we innovatively apply an Age-Period-Cohort model which accounts for spatial trends and the complex survey design of the data to estimate subnational U5MRs in Kenya. After validating our results against current methods, the inclusion of cohort can provide new insights into U5MRs. We ensure our method is flexible and can be applied to other LMICs.

Original language	English
Article number	100708
Number of pages	11
Journal	Spatial and Spatio-temporal Epidemiology
Volume	52
Early online date	13 Dec 2024
DOIs	https://doi.org/10.1016/j.sste.2024.100708
Publication status	Published - 1 Feb 2025

Data Availability Statement

Data from the DHS is free to download after registration with a suitable project that allows access to the Kenyan dataset specifically. The full code for implementing the APC (and any other) model considered in this paper can be found at https://github.com/connorgascoigne/Subnational-U5MR-with-APC-models.

Acknowledgements

The authors would like acknowledge Alana McGovern, Zehang Richard Li and Yunhan Wu for their help with producing the results for the direct estimates, Fay–Herriot estimates and subnational weights for proportional aggregation. Furthermore, the authors are grateful for the insightful suggestions of the two referees and editor who helped improve this manuscript.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Age-period-cohort
Complex surveys
Space–time smoothing
Stratified cluster sampling
Under-five mortality rates

ASJC Scopus subject areas

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

Access to Document

10.1016/j.sste.2024.100708Licence: CC BY

Cite this

@article{198839004cd943a7ae8f8682d6f5b099,

title = "Estimating subnational under-five mortality rates using a spatio-temporal Age-Period-Cohort model",

abstract = "Subnational estimates of under-five mortality rates (U5MRs) are a vital statistic for the United Nations to reduce mortality inequalities between high-income and Low-and-Middle Income Countries (LMICs). Current methods of modelling U5MR in LMICs smooth across trends in age and year of death, but not birth-cohort, to reduce uncertainty in estimates caused by data-sparsity. Using survey data from Kenya, we innovatively apply an Age-Period-Cohort model which accounts for spatial trends and the complex survey design of the data to estimate subnational U5MRs in Kenya. After validating our results against current methods, the inclusion of cohort can provide new insights into U5MRs. We ensure our method is flexible and can be applied to other LMICs.",

keywords = "Age-period-cohort, Complex surveys, Space–time smoothing, Stratified cluster sampling, Under-five mortality rates",

author = "Connor Gascoigne and Theresa Smith and Jon Wakefield and John Paige",

year = "2025",

month = feb,

day = "1",

doi = "10.1016/j.sste.2024.100708",

language = "English",

volume = "52",

journal = "Spatial and Spatio-temporal Epidemiology",

issn = "1877-5845",

publisher = "Elsevier",

}

TY - JOUR

T1 - Estimating subnational under-five mortality rates using a spatio-temporal Age-Period-Cohort model

AU - Gascoigne, Connor

AU - Smith, Theresa

AU - Wakefield, Jon

AU - Paige, John

PY - 2025/2/1

Y1 - 2025/2/1

N2 - Subnational estimates of under-five mortality rates (U5MRs) are a vital statistic for the United Nations to reduce mortality inequalities between high-income and Low-and-Middle Income Countries (LMICs). Current methods of modelling U5MR in LMICs smooth across trends in age and year of death, but not birth-cohort, to reduce uncertainty in estimates caused by data-sparsity. Using survey data from Kenya, we innovatively apply an Age-Period-Cohort model which accounts for spatial trends and the complex survey design of the data to estimate subnational U5MRs in Kenya. After validating our results against current methods, the inclusion of cohort can provide new insights into U5MRs. We ensure our method is flexible and can be applied to other LMICs.

AB - Subnational estimates of under-five mortality rates (U5MRs) are a vital statistic for the United Nations to reduce mortality inequalities between high-income and Low-and-Middle Income Countries (LMICs). Current methods of modelling U5MR in LMICs smooth across trends in age and year of death, but not birth-cohort, to reduce uncertainty in estimates caused by data-sparsity. Using survey data from Kenya, we innovatively apply an Age-Period-Cohort model which accounts for spatial trends and the complex survey design of the data to estimate subnational U5MRs in Kenya. After validating our results against current methods, the inclusion of cohort can provide new insights into U5MRs. We ensure our method is flexible and can be applied to other LMICs.

KW - Age-period-cohort

KW - Complex surveys

KW - Space–time smoothing

KW - Stratified cluster sampling

KW - Under-five mortality rates

UR - https://www.scopus.com/pages/publications/85212157380

U2 - 10.1016/j.sste.2024.100708

DO - 10.1016/j.sste.2024.100708

M3 - Article

SN - 1877-5845

VL - 52

JO - Spatial and Spatio-temporal Epidemiology

JF - Spatial and Spatio-temporal Epidemiology

M1 - 100708

ER -

Estimating subnational under-five mortality rates using a spatio-temporal Age-Period-Cohort model

Abstract

Data Availability Statement

Acknowledgements

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this