Accurate and reliable estimates of mortality outcomes are essential in monitoring progress over time and understanding disparities across populations. However, in many cases trends may be unclear due to poor quality or noisy data. I present a hierarchical framework to estimate mortality at the subnational level. The model builds on characteristics age patterns in mortality, while also allowing for both spatial and temporal patterns to be taken into account. The methodology is used to investigate racial differences in the current US opioid epidemic, with results suggesting strong spatial patterns in racial inequalities.

Monica Alexander is a PhD candidate in demography at UC Berkeley. Her research interests include statistical demography, and health and mortality inequalities. She has Masters degrees in Statistics (from Berkeley) and Social Research (from the Australian National University). She has worked on global health and demographic research with organisations such as UNICEF, the World Health Organization, and the Human Mortality Database.