An Application of Bayesian Methods to Small-Area Estimates of Poverty Rates

Joey Campbell, University of Texas at San Antonio
Corey S. Sparks, University of Texas at San Antonio

Efforts to estimate various sociodemographic variables in small geographical areas have proven difficult with the replacement of the Census long form with the American Community Survey (ACS). ACS data products promise to begin providing up-to-date profiles of the nation's population and economy; however, the design has left researchers with significant gaps in sub-national coverage resulting in unreliable estimates for basic demographic measures. Borrowing information from neighboring areas and across time with a spatiotemporal smoothing process based on Bayesian statistical methods, it is possible to generate more stable estimates of rates for geographic areas not represented in the ACS. This research evaluates this spatiotemporal smoothing process in its ability to derive estimates of poverty rates at the county level for the contiguous United States. These estimates are compared to more traditional estimates from the Census, and error rates are calculated which substantiate the practical application of this smoothing method.