Estimating zonal-level hemoglobin levels for women and children using the bivariate Fay-Herriot model

Anemia remains a major public health concern in Ethiopia, particularly among women of reproductive age and children, with substantial variation across local administrative zones. Reliable small-area estimates of hemoglobin levels are essential for evidence-based health planning; however, direct survey estimates are often unreliable at disaggregated levels due to small sample sizes and high variability. This study applies a bivariate small area estimation (SAE) approach to improve the precision of hemoglobin level estimates for women and children by exploiting their inherent correlation. Data were obtained from the Ethiopian Demographic and Health Survey (EDHS) and auxiliary variables from the Population and Housing Census. The analysis employed the Bivariate Fay-Herriot (BFH) model to jointly model hemoglobin levels, allowing information sharing through both census covariates and the correlation between outcomes. Model performance was compared with the Univariate Fay-Herriot (UFH) model and traditional direct survey estimates. The results show that the BFH model provides more stable and precise estimates than both UFH and direct methods, demonstrating the benefits of borrowing strength across correlated health indicators. These findings highlight the value of bivariate modeling in enhancing the reliability of local-level health estimates and reducing uncertainty in survey-based measures. Accurate subnational hemoglobin estimates can support policymakers in designing targeted interventions for anemia reduction. The study encourages the use of multivariate SAE frameworks in future health research and national surveys to improve data-driven decision-making and monitoring of public health outcomes.