210298 Design and Analysis of a Dual-Frame Telephone Survey—combining cell phone and RDD samples

Monday, November 9, 2009: 9:10 AM

Bo Lu, PhD , College of Public Health, The Ohio State University, Columbus, OH
  
Cell phone use has grown quickly in the past decade. According to National Health Interview Survey (NHIS) estimate, there are 14.5% of adults residing in cell-only households in the second half of 2007. Therefore, the representativeness of the traditional RDD landline survey is being questioned due to the increased popularity of cell phone use. Realizing this trend, more and more large state-based surveys have started to include a cell phone supplement sample in addition to the RDD sample. Such design is referred as dual-frame survey because samples are drawn independently from two overlapping sampling frames to cover the population of interest. Based on our experience with Ohio Family Health Survey (OFHS) 2008, we summarize the issues and challenges involved in the design and analysis of dual-frame survey and review the popular estimation methods through a simulation study.

Learning Objectives:
Describe the advantages of including a cell phone sample in a telephone survey. Discuss the challenges to weighting the data.

Keywords: Survey, Methodology

Presenting author's disclosure statement:

Qualified on the content I am responsible for because: I am a statistician who has taught survey sampling and is acting as a consultant on a large survey project in Ohio.
Any relevant financial relationships? No

I agree to comply with the American Public Health Association Conflict of Interest and Commercial Support Guidelines, and to disclose to the participants any off-label or experimental uses of a commercial product or service discussed in my presentation.

See more of: Statistical Issues and Challenges with Health Insurance Surveys
See more of: Statistics