A spatial variance-smoothing area level model for small area estimation of demographic rates

TL;DR

This paper introduces a hierarchical Bayesian spatial model that improves small area estimates of demographic proportions by smoothing both means and estimated sampling variances, accounting for uncertainty in survey data.

Contribution

It presents a novel spatial variance-smoothing area level model that explicitly accounts for variability in estimated sampling variances for small area demographic estimation.

Findings

Model improves precision of small area estimates.

Demonstrated effectiveness with vaccination and HIV data.

Provides reliable interval estimates accounting for variance uncertainty.

Abstract

Accurate estimates of subnational health and demographic indicators are critical for informing health policy decisions. Many countries collect relevant data using complex household surveys, but when data are limited, direct survey weighted estimates of small area proportions may be unreliable. Area level models treating these direct estimates as response data can improve precision but often require known sampling variances of the direct estimators for all areas. In practice, the sampling variances are typically estimated, so standard approaches do not account for a key source of uncertainty. In order to account for variability in the estimated sampling variances, we propose a hierarchical Bayesian spatial area level model that smooths both the estimated means and sampling variances to produce point and interval estimates of small area proportions. Our model explicitly targets estimation of small area proportions rather than means of continuous variables and we consider examples of both moderate and low prevalence events. We demonstrate the performance of our approach via simulation and application to vaccination coverage and HIV prevalence data from the Demographic and Health Surveys.