Hot spots, cluster detection and spatial outlier analysis of teen birth rates in the U.S., 2003–2012. (June 2017)

• Record Type: Journal Article
• Authors: Khan, Diba; Rossen, Lauren M.; Hamilton, Brady E.; He, Yulei; Wei, Rong; Dienes, Erin
• Is Part Of: Spatial and spatio-temporal epidemiology. Volume 21(2017)
• Page Start: 67
• Page End: 75
• Publication Date: 2017-06
• Subjects: Bayesian -- Hotspots -- Spatial outliers; Epidemiology -- Statistical methods -- Periodicals; Epidemiology -- Periodicals; 614.4072
• DOI: 10.1016/j.sste.2017.03.002
• Languages: English
• ISSNs: 1877-5845

Abstract

Abstract: Teen birth rates have evidenced a significant decline in the United States over the past few decades. Most of the states in the US have mirrored this national decline, though some reports have illustrated substantial variation in the magnitude of these decreases across the U.S. Importantly, geographic variation at the county level has largely not been explored. We used National Vital Statistics Births data and Hierarchical Bayesian space-time interaction models to produce smoothed estimates of teen birth rates at the county level from 2003–2012. Results indicate that teen birth rates show evidence of clustering, where hot and cold spots occur, and identify spatial outliers. Findings from this analysis may help inform efforts targeting the prevention efforts by illustrating how geographic patterns of teen birth rates have changed over the past decade and where clusters of high or low teen birth rates are evident.