A Comparative Evaluation of Traditional Listing vs. Address-Based Sampling Frames: Matching with Field Investigation of Discrepancies

• Activity Number: 421
• Type: Contributed
• Date/Time: Wednesday, August 5, 2009 : 8:30 AM to 10:20 AM
• Sponsor: Section on Survey Research Methods
• Author(s): Jill Montaquila*+ and Michael J. Brick and Valerie Hsu and Stephanie Eckman and Ned English
• Companies: Westat, Inc. and Westat, Inc. and Westat, Inc. and NORC at the University of Chicago and NORC at the University of Chicago
• Keywords: Delivery Sequence File ; coverage

Abstract

Increasingly, survey practitioners are considering the use of address-based sampling frames for household surveys. These frames are being studied as alternatives to random digit dial (RDD) frames, to facilitate the use of mixed-mode methods, and to supplement or replace traditional listing of addresses. The recent consideration of these frames has been made possible by the availability of files based on the United States Postal Service (USPS) Delivery Sequence File (DSF) and changes in addressing, particularly those resulting from the development of Enhanced-911 systems. Previous studies have, collectively, yielded an abundance of information about the utility of address-based sampling frames, and it has been critical to continue evaluating these frames in light of the ongoing changes in addressing. This paper extends the earlier results by evaluating the USPS-based address frame.