Comparison of NSDUH Population Percentages from the United States, Census Regions, States, and the District of Columbia

• Activity Number: 596 - Advances in Small Area Estimation
• Type: Contributed
• Date/Time: Wednesday, August 1, 2018 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Kathy Spagnola* and Matthew Williams and Akhil Vaish and Neeraja Sathe
• Companies: RTI International and SAMHSA/CBHSQ and RTI International and RTI International
• Keywords: small area estimation (SAE); substance use; mental health; National Survey on Drug Use and Health (NSDUH); p value

Abstract

The National Survey on Drug Use and Health (NSDUH) is an annual survey that is the primary source of information on substance use and mental health measures for the U.S. civilian, noninstitutionalized population aged 12 years old or older. Each year, state small area estimates are produced using 2 years of NSDUH data for various substance use, mental health, use disorder, and treatment outcomes. These state-level estimates are very useful to state leaders and researchers. In addition to state small area estimates, estimates are produced for the total United States and the four census regions. Because data users often want to know how a given state's estimates compare with the nation's estimates as a whole, with estimates from a census region (e.g., California vs. the West region), or with another nearby state (e.g., California vs. Oregon), comparisons were done between population percentages from the United States, census regions, and states (including the District of Columbia). This paper briefly discusses the methodology for doing these comparisons, and a few comparisons are presented as examples for several outcomes.