Logistic Regression Type Small Area Estimations Based on Relative Error

A Hierarchical Bayesian approach to small area estimation of health insurance coverage in Ethiopian administrative zones for better policies and programs

Sample surveys are extensively used to provide reliable direct estimates for large areas or domains with enough sample sizes at national and regional levels. However, zones are unplanned domains by the Demographic and Health Survey (DHS) program and need more sample sizes to produce direct survey estimates with adequate precision. Conducting surveys in small areas (like zones) is too expensive and time-consuming, making it unfeasible for developing countries like Ethiopia. Therefore, this study aims to use the Hierarchical Bayes (HB) Small Area Estimation (SAE) model to estimate the Community-Based Health Insurance (CBHI) coverage at the zone levels in Ethiopia. To achieve this, we combined the 2019 Ethiopia Mini-Demographic and Health Survey (EMDHS) data with the 2007 population census data. SAE has addressed the challenge of producing reliable parameter estimates for small or even zero sample sizes across Ethiopian zones by utilizing auxiliary information from the population census. The results show that model-based estimates generated by the SAE approach are more accurate than direct survey estimates of CBHI. A map of CBHI scheme coverage was also used to visualize the spatial variation in the distribution of CBHI scheme coverage. From the CBHI scheme coverage map, we noticed notable variations in CBHI scheme coverage across Ethiopian zones. Additionally, this research identified areas with high and low CBHI scheme coverage to improve decision-making and increase coverage in Ethiopia. One of the novelties of this paper is estimating the non-sampled zones; therefore, the policymakers will give equal attention similar to the sampled zones.