Using Statistical Process Control Techniques in the American Community Survey

• Activity Number: 397
• Type: Topic Contributed
• Date/Time: Tuesday, August 2, 2011 : 2:00 PM to 3:50 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Steven Hefter*+ and Erica Marquette
• Companies: U.S. Census Bureau and U.S. Census Bureau
• Keywords: ACS ; Statistical Process Control ; Error

Abstract

Each year the American Community Survey collects data about roughly two million housing units, 4.5 million people in the household population, and 150,000 people in group quarters facilities. We have begun developing automated statistical process control methods to uncover potential errors in the data. Several methodologies are being used to investigate responses from all three data collection modes (mail, Computer Assisted Telephone Interview (CATI), and Computer Assisted Personal Interview (CAPI)) using traditional Shewhart charts. For mail, we compare the individual responses of each question at various levels of geography. For CATI, we use similar methods, but also compare data for each telephone center. For the CAPI data collection mode we concentrated our initial efforts on Field Representative (FR) item missing data rates and compare each FR to all FRs within clusters of counties.