Use of Paradata to Assess the Performance of a Multi-Mode ABS Study

• Activity Number: 65
• Type: Topic Contributed
• Date/Time: Sunday, July 31, 2011 : 4:00 PM to 5:50 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Ting Yan*+ and Rupa Datta and Kirk M. Wolter and Hee-Choon Shin
• Companies: NORC at the The University of Chicago and NORC at the The University of Chicago and NORC at the The University of Chicago and NORC at the The University of Chicago
• Keywords: address based sampling ; multi-mode design ; paradata

Abstract

Address-based sampling (ABS) surveys are gaining popularity relative to landline RDD surveys because they provide better coverage (or representation) of U.S. residential households and the people who live in them. ABS surveys typically entail a multi-mode data collection approach, and there is considerable flexibility to structure the approach. However, the use of multiple modes of data collection requires that the survey organization have a strict control on where sample cases end up. Paradata are data created during the data collection process and can be used to monitor sample performance, case flow, and efficiency of the survey design. This paper discusses the collection and the use of paradata (such as call records data and interviewer observations) to monitor and assess the performance of an ABS study targeting households with at least one child under the age of 13.