ABS and Demographic Flags: Examining the Implications for Using Auxiliary Frame Information

• Activity Number: 597
• Type: Topic Contributed
• Date/Time: Thursday, August 7, 2014 : 8:30 AM to 10:20 AM
• Sponsor: Survey Research Methods Section
• Author(s): Jamie Ridenhour*+ and Joseph P. McMichael and Jill Dever and Rachel Harter
• Companies: RTI International and RTI International and RTI International and RTI International
• Keywords: ABS ; address-based sampling ; auxiliary data

Abstract

Auxiliary information from marketing databases can be applied to an ABS frame to identify addresses likely to house the target population for a particular survey. If this information is sufficiently accurate, these data can be used to stratify addresses and efficiently target the eligible population. This paper evaluates the accuracy of auxiliary information based on data from the Evaluation of Public Education Campaign on Teen Tobacco (ExPECTT), an in-person household survey targeting youths ages 11-16. Addresses flagged as likely to have a member of the target population were assigned to a high likelihood stratum and those flagged as not likely as well as those without auxiliary information were assigned to a low likelihood stratum. Because the auxiliary information is untested and high coverage desirable, ExPECTT includes addresses sampled from strata with presumed high and low likelihood of being in the target population. In this paper, we explore demographic characteristics and key outcomes of youths in households from high likelihood addresses with those in the low likelihood stratum. We also comment on the impact of the auxiliary information on data collection efficiencies.