State and Local Wireless and Landline Estimates

• Activity Number: 129
• Type: Contributed
• Date/Time: Monday, August 1, 2011 : 8:30 AM to 10:20 AM
• Sponsor: Section on Survey Research Methods
• Author(s): Nadarajasundaram Ganesh*+ and Michael Davern and Stephen Blumberg and Julian Luke and Miche Boudreaux and Karen Soderberg
• Companies: NORC at the The University of Chicago and NORC at the The University of Chicago and Centers for Disease Control and Prevention and Centers for Disease Control and Prevention and University of Minnesota and University of Minnesota
• Keywords: NHIS ; Small Area Estimation ; State Wireless Prevalence Estimates

Abstract

High-quality state-level prevalence estimates of wireless-only, wireless-mostly, landline-mostly, landline-only and non-telephone households are essential when weighting data from random-digit-dial telephone surveys conducted at the state level. Currently these estimates are available from the National Health Interview Survey (NHIS) at only the national and regional level. We will present recent state and local model-based wireless and landline estimates, produced using a combination of January 2007-June 2010 NHIS data, 2006-2009 American Community Survey data, and 2007-2010 data on listed households from infoUSA.com. We discuss our methods and observed efficiency gains using our modeling approach, and we present graphs/choropleth maps indicating changes over time. Finally, we discuss limitations of our modeling approach and also possible future improvements.