Spatio-Temporal Change of Support Modeling for the American Community Survey with R

Spatio-temporal change of support (STCOS) methods are designed for statistical inference and prediction on spatial and temporal domains which may differ from those of the observed data. Bradley, Wikle, and Holan (2015; Stat) introduced a parsimonious class of Bayesian hierarchical spatio-temporal models for STCOS for Gaussian data through a motivating application to the American Community Survey (ACS), an ongoing survey administered by the U.S. Census Bureau that measures key socioeconomic and demographic variables for various populations in the United States. The methodology offers a principled approach to compute model-based estimates, along with associated measures of uncertainty, for ACS variables of interest on customized geographies and/or time periods. However, users of ACS data who are unfamiliar with spatio-temporal models could find the notion of implementing them to be somewhat challenging. The present work seeks to bridge this gap by guiding readers through STCOS computations in a detailed case-study. We focus on the R computing environment because of its popularity, free availability, and high quality contributed packages for geographic processing, data manipulation, and more. We introduce the stcos package to facilitate computations for the STCOS model. By providing a detailed guide through STCOS computations, the methodology will become more broadly accessible to federal statistical agencies such as the Census Bureau, the ACS data-user community, and the general R-user community.