The Poisson Change of Support Problem with Applications to the American Community Survey

• Activity Number: 18
• Type: Topic Contributed
• Date/Time: Sunday, August 3, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Jonathan R. Bradley*+ and Christopher K. Wikle and Scott Holan
• Companies: University of Missouri and University of Missouri and University of Missouri
• Keywords: support ; Markov chain Monte Carlo ; hierarchical ; non-Gaussian

Abstract

The American Community Survey (ACS) is an ongoing survey administered by the U.S. Census Bureau that provides timely information on several key demographic variables. Specifically, the ACS produces 1-year, 3-year, and 5-year "period-estimates," and corresponding margins of errors, of various random variables recorded over the U.S. (e.g., median age, race, median income, veteran status, etc.). The 1-year, 3-year, and 5-year period estimates are defined on different levels of geography depending on the population size. Despite the availability of different choices for the estimate's spatial support, it would be useful for ACS users to be able to specify their own spatial support. We propose Bayesian spatial change of support methodology for count data that allows users of ACS to define their own spatial support. We demonstrate the effectiveness of our approach through a simulated example as well as through an analysis of data from the ACS.