The Global Adult Tobacco Survey (GATS): Sample Design and Related Methods

• Activity Number: 314
• Type: Contributed
• Date/Time: Tuesday, August 3, 2010 : 8:30 AM to 10:20 AM
• Sponsor: Section on Survey Research Methods
• Author(s): William D. Kalsbeek*+ and J. Michael Bowling and Krishna M. Palipudi
• Companies: The University of North Carolina at Chapel Hill and The University of North Carolina at Chapel Hill and CDC
• Keywords: sample design ; health surveys ; survey nonresponse ; sample weights

Abstract

Begun in 2007 as a part of the Global Tobacco Surveillance System, GATS is a growing collection of comparably designed national surveys on tobacco use behavior, currently in 14 countries around the world. This system of periodic cross-sectional surveys has been developed as the main data source for planning and evaluating various efforts to reduce tobacco use in each country. Our paper reviews the design rationale and the sampling-related challenges in developing this system. We specifically emphasize common sample design features to each GATS survey and the statistical basis for GATS sample size requirements. We also discuss the process used to compute sample weights, present a summary of some key sampling and recruitment outcomes from eight GATS countries that have released their survey findings, and comment on some of the lessons learned thus far.