Comparison of Mixed-Mode and Address Frame Designs to Random Digit Dialing for General Population Surveys

• Activity Number: 195
• Type: Contributed
• Date/Time: Monday, August 7, 2006 : 2:00 PM to 3:50 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Michael W. Link*+ and Michael P. Battaglia and Martin R. Frankel and Larry Osborn
• Companies: Centers for Disease Control and Prevention and Abt Associates Inc. and Abt Associates Inc. and Abt Associates Inc.
• Keywords: random-digit dialing (RDD) ; telephone surveys ; response rates ; mixed modes ; survey sampling

Abstract

Multiple modes and address-based sampling may be viable alternatives to random digit dialing (RDD) for general population surveys. A 6 state pilot conducted as part of the Behavioral Risk Factor Surveillance System (BRFSS) compared two designs to RDD: (1) telephone numbers selected using RDD and reverse-matched for addresses, (2) addresses sampled from a postal database and matched to telephone numbers. For both, surveys were mailed to all identified addresses, with telephone follow-up of nonrespondents. Those without an identifiable address were contacted by telephone. The pilots were conducted in parallel with the RDD-based BRFSS survey, providing a baseline for comparison. The pilot designs and RDD survey are compared on response rates; respondent representativeness, including reaching cell phone-only households and those without telephones; and, comparability of survey estimates.