Spatial Modeling for Small-Area Poverty Analysis

• Activity Number: 436
• Type: Contributed
• Date/Time: Tuesday, August 6, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Social Statistics Section
• Author(s): Jasen A Taciak*+ and Lauren Bowers and Amanda Bell Beal and Dimitris Polis
• Companies: US Census Bureau and US Census Bureau and US Census Bureau and US Census Bureau
• Keywords: small area estimation ; poverty ; SAIPE ; American Community Survey ; spatial analysis

Abstract

The Small Area Income and Poverty Estimates program of the U.S. Census Bureau currently produces poverty estimates for school districts using a tiered approach. A Fay-Herriott approach is used to produce poverty count estimates at the county level, which are then synthetically allocated to the school district level using both survey and administrative records data. The synthetic approach for the sub-county estimation is driven by the limited availability of administrative data identified to sub-county domains. Recent improvements in the processing of such data has made stochastic modeling of sub-county domains feasible. Such areas are much smaller, both in geographic extent, and in sample size for the direct estimate, however. Geospatial smoothing techniques across areas will likely be more important at this level of analysis. This paper will examine a series of geographic weighting schemes based not only on proximity between neighboring areas, but also measures of geographic clustering/interdependence based on demographic and socioeconomic characteristics.