Using Census Public Use Microdata Areas (PUMAs) as Primary Sampling Units in Area Probability Household Surveys

• Activity Number: 251
• Type: Contributed
• Date/Time: Monday, August 10, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Joseph McMichael and Patrick Chen*
• Companies: RTI International and RTI International
• Keywords: Household Survey ; Primary Sampling Units ; PUMA PSU ; Area Sampling

Abstract

Multi-stage cluster designs are employed in area probability household surveys. Samples of primary sampling units (PSUs) are selected at the first stage; within a PSU, smaller geographical areas are selected at subsequent stages; and households are selected at the final stage. Many area probability household surveys use single counties or a combination of contiguous counties is used as PSU. The Census Public Use Microdata Areas (PUMAs) are defined for the dissemination of Census public use microdata and American Community Survey (ACS) data. We used the PUMAs as PSUs in two national surveys. In this paper, we describe the benefits of using PUMAs as PSUs instead of counties. We also present the results of two simulation studies designed to address concerns (the field costs and the coverage of major metropolitan areas) with using PUMAs as PSUs.