An Empirical Study to Evaluate the Performance of Synthetic Estimates of Substance Use in the National Survey on Drug Use and Health

• Activity Number: 249
• Type: Contributed
• Date/Time: Monday, August 5, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Akhil Vaish*+ and Neeraja Sathe and Kathryn Spagnola and Ralph Folsom and Art Hughes
• Companies: RTI International and RTI International and RTI International and RTI International and Center for Behavioral Health Statistics and Quality, SAMHSA
• Keywords: Small area estimation ; design-based estimates ; model-based estimates ; synthetic estimates ; National Survey on Drug Use and Health (NSDUH) small area estimates

Abstract

Small area estimation methods are used to produce State and substate estimates of substance use and mental disorders using data from the National Survey on Drug Use and Health. Design-based estimates could be used as an alternative because they are less expensive than small area estimates and take less time to produce. Thus, it is important to determine how the small area estimates compare with their design-based counterparts in terms of accuracy and precision. A previous study demonstrated that small area estimates were generally more precise than design-based estimates while exhibiting only small levels of bias. In this paper, those results are extended by conducting an additional simulation study to evaluate the performance of synthetic estimates. These estimates are commonly produced for small areas where no sample data can be obtained, and this study aims to provide some guidance about the quality of such estimates.