Dual-Frame Weights (Landline and Cell) for the 2009 Minnesota Health Access Survey

• Activity Number: 159
• Type: Topic Contributed
• Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Kanru Xia*+ and Steven Pedlow and Michael Davern
• Companies: NORC and NORC and NORC
• Keywords: dual frame ; composite weighting

Abstract

In recent years, the increasing undercoverage of random-digit-dial (RDD) landline frames has driven surveys to employ landline plus cell phone dual-frame designs. The 2009 Minnesota Health Access Survey, a large-scale health insurance survey conducted jointly by the Minnesota Department of Health and the University of Minnesota, collected 9,811 landline interviews and 2,220 interviews via a cell phone sample (regardless of landline/cell phone usage). This paper compares weights produced under four different screening strategies (RDD-only, RDD plus cell-only, RDD plus cell-only/cell-mostly, and RDD plus cell-any) and five different weighting adjustments for combining landline and cell-phone interviews. Results show the lowest mean-squared errors result from using all interviews with an effective sample size adjustment factor.