Project Results: Working with over 2 million births from the North Carolina Birth Records Database, as well as block-group level socioeconomic indicators from the Census and American Community Survey, the team used spatial-statistics techniques to find 'hotspots' corresponding to clusters of births in specific categories. They then showed significant connections between socioeconomic indicators and cluster membership. Finally, they employed cutting-edge machine-learning techniques to quantify the distributional differences between births in different demographic categories.
Partially funded by the Sanford School of Public Policy
Project Manager: Lizzy Huang