A Bayesian Hierarchical Model to Estimate and Project Subnational Populations of Women of Reproductive Age

Monica Alexander, University of California, Berkeley

Accurate estimates of subnational populations are important for policy formulation and monitoring population health indicators. In particular, estimates of the number of women of reproductive age affect measures of maternal mortality, contraceptive prevalence and fertility. However, in many developing countries, data on population counts are limited and are of poor quality, and so levels are unclear. We present a Bayesian hierarchical model to estimate female populations at the subnational level. The model builds on a cohort component projection framework, incorporates data on population counts and migration, and uses characteristic mortality schedules to obtain population estimates and uncertainty levels. The model is applied to estimate and project populations by county in Kenya for 1979-2020.

Presented in Session 11: Probabilistic Methods: Fertility, Mortality, and Migration