Total Survey Error: Past, Present, and Future

• Activity Number: 49
• Type: Invited
• Date/Time: Sunday, August 7, 2005 : 4:00 PM to 5:50 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Paul Biemer*+ and Robert Groves*+ and Alan Zaslavsky*+ and William D. Kalsbeek*+
• Companies: RTI International and University of Michigan and Harvard University and University of North Carolina, Chapel Hill
• Keywords: nonsampling error ; survey quality ; mean squared error ; nonresponse bias ; measurement bias ; survey models

Abstract

On March 17--18, 2005, the National Institute of Statistical Sciences, in conjunction with SAMSI, held a two-day workshop dedicated to the measurement of total survey error. Total survey error includes both sampling and nonsampling errors, examples of the latter being biases introduced by nonresponse, mode effects, frame undercoverage, or data recording errors. The purpose of this workshop was to bring together researchers from federal agencies, academia, and survey organizations to discuss methods for measuring nonsampling errors. Participants discussed the types of nonsampling errors they experience and, therefore, seek to quantify. Academic participants, as well as participants from the agencies and survey organizations, presented methods for quantifying components of total survey error. By bringing together participants and researchers from different perspectives, we hoped to stimulate research into this underdeveloped and important area of survey research. In this session, the workshop organizer, Paul Biemer, will describe some of the highlights of the event.