Using Statistical Models in Place of Clerical Matching in the Census 2020 Post-Enumeration Survey to Produce Estimates of Census Housing Unit Coverage

• Activity Number: 242 - Issues in Frame Quality and Accuracy Assessments
• Type: Contributed
• Date/Time: Monday, July 29, 2019 : 2:00 PM to 3:50 PM
• Sponsor: Government Statistics Section
• Author(s): Michael Beaghen* and Elizabeth Marra and Mark Jost
• Companies: and U.S. Census Bureau and U.S. Census Bureau
• Keywords: Census coverage error; dual-system estimation; record linkage

Abstract

The Census Bureau will conduct a Post-Enumeration Survey (PES) to assess the 2020 Census' coverage of population and housing units (HU). Census HU coverage errors include omissions, duplication, HUs enumerated in the wrong place, and HUs that should not have been enumerated. The 2020 PES will be a probability sample of about 170,000 HUs nationwide. PES methodology requires an Independent Listing of HUs and people in HUs in a sample of geographies. This independence is necessary to satisfy the requirements for the dual-system estimator. The PES listings are matched to the census listings of HUs and people. Accurate matching includes automated, probability based matching, followed by clerical matching, and by field interviewing to resolve differences in the listings. Since the clerical matching operations are time consuming and expensive, successful models to replace them could save time and money in future Census coverage measurement programs.