ABS and Cell Phones: Appending Both Cell Phone and Landline Phone Numbers to an Address-Based Sampling Frame

• Activity Number: 140
• Type: Contributed
• Date/Time: Monday, July 30, 2012 : 8:30 AM to 10:20 AM
• Sponsor: Section on Survey Research Methods
• Author(s): Joseph McMichael*+ and Sue Pedrazzani and Gina Kilpatrick and Matthew Strobl
• Companies: RTI International and RTI International and RTI International and RTI International
• Keywords: Address-based sampling ; ABS ; cell phone ; multi-mode ; mixed-mode ; bias

Abstract

Address-based sampling (ABS) frames can support a wide variety of survey designs due to the information that can be appended to a mailing address. This information allows for a variety of contact and data collection modes, including mail, landline telephone, web, and in-person. As researchers experiment with and debate these methods, the amount of available data that can be appended to address files has increased and, in most cases, improved in its quality and completeness.

Cell phone appends are new to the ABS survey. This paper summarizes our experience appending cell phones to an ABS sample, including productivity and efficacy of the numbers. We will detail raw append rates and the accuracy of those appends. We also discuss vendor sources of cell phone, how the numbers are collected by vendors and speculate on potential for bias.

This paper describes our experience from the National Children's Study in the Los Angeles County Area (LA NCS). The pilot phase of the LA NCS employed an address-based sample comprising more than 14,000 households. The LA NCS consisted of a multi-mode recruitment and data collection effort that included mail, telephone, and in-person protocols.