Evaluation of Data from the American Community Survey and the Current Population Survey

• Activity Number: 251
• Type: Contributed
• Date/Time: Tuesday, August 13, 2002 : 2:00 PM to 3:50 PM
• Sponsor: Section on Government Statistics*
• Author(s): Stephen Wenck*+ and Sameena Salvucci and Kevin Deardorff and Angela Brittingham
• Affiliation(s): Synectics for Management Decisions, Inc. and Synectics for Management Decisions, Inc. and U.S. Census Bureau and U.S. Census Bureau
• Keywords: Reliability ; Current Population survey ; American Community Survey ; Comparability

Abstract

The American Community Survey (ACS) is designed to demonstrate the feasibility of collecting long form type information at the same time as, but separate from, the Decennial Census. The ACS will provide the same sort of data as the census long form, updated every year. With a nationwide sample of three million addresses, the ACS can provide demographic, social, economic and housing profiles annually for areas and subgroups with 65,000 or more people. Releasing data from the ACS encourages input from the Census Bureau's national partners and interested groups about the usefulness of the information for national, state, and local policy decisions. This paper evaluates the reliability of data from the ACS by systematically comparing various socioeconomic characteristics with those from other published survey and decennial census data. This paper examined data that are directly relevant to the specific groups for which the Census Bureau regularly creates socioeconomic reports (i.e., Hispanics, Blacks, aging population, women).