A0370
Title: Bayesian projections of proportions with limited data: A subnational application to contraceptive supply shares
Authors: Hannah Comiskey - Monash University (Australia) [presenting]
Worapree Ole Maneesoonthorn - Monash University (Australia)
David Frazier - Monash University (Australia)
Abstract: Engaging the private sector in contraceptive method supply is critical for creating equitable, sustainable, and accessible healthcare systems. To achieve this, it is essential to understand where women obtain their modern contraceptives. While national-level estimates provide valuable insights into overall trends in contraceptive supply, they often obscure significant variations within subnational regions. As more countries adopt decentralized models for family planning services, reliable subnational data is essential for effective monitoring and decision-making. However, a lack of reliable and regularly collected subnational data hampers progress. To bridge this gap, a novel approach is proposed that leverages latent attributes in Demographic and Health Survey (DHS) data to produce Bayesian probabilistic projections of contraceptive method supply shares (public vs. private) with limited data. The modeling framework is built on Bayesian hierarchical models. Using penalized splines to track supply shares over time, the spatial nature of the data is leveraged, and a correlation structure is incorporated between recent supply share observations at national and subnational levels. This framework contributes to the domain of subnational estimation of proportions in data-sparse settings, outperforming comparable approaches. To the best of knowledge, it is the first model designed specifically to estimate contraceptive supply shares at this administrative level.
