Estimating Subnational Under-Five Mortality Rates Using a Spatio-Temporal Age-Period-Cohort Model

TL;DR

This paper introduces a novel Bayesian Age-Period-Cohort model to improve subnational under-five mortality rate estimates by incorporating cohort effects, validated using Kenyan DHS data.

Contribution

It extends existing smoothing methods by including cohort effects in a hierarchical model for more accurate subnational U5MR estimates.

Findings

Cohort effects improve U5MR estimation accuracy.

Model accounts for complex survey design.

Validated against direct estimates.

Abstract

Producing subnational estimates of the under-five mortality rate (U5MR) is a vital goal for the United Nations to reduce inequalities in mortality and well-being across the globe. There is a great disparity in U5MR between high-income and Low-and-Middle Income Countries (LMICs). Current methods for modelling U5MR in LMICs use smoothing methods to reduce uncertainty in estimates caused by data sparsity. This paper includes cohort alongside age and period in a novel application of an Age-Period-Cohort model for U5MR. In this context, current methods only use age and period (and not cohort) for smoothing. With data from the Kenyan Demographic and Health Surveys (DHS) we use a Bayesian hierarchical model with terms to smooth over temporal and spatial components whilst fully accounting for the complex stratified, multi-staged cluster design of the DHS. Our results show that the use of cohort may be useful in the context of subnational estimates of U5MR. We validate our results at the subnational level by comparing our results against direct estimates.