Health United States 2020-2021

National Survey on Drug Use and Health (NSDUH)

Substance Abuse and Mental Health Services Administration


NSDUH reports on the prevalence, incidence, and patterns of illicit drug use and alcohol use among the civilian noninstitutionalized U.S. population aged 12 years and over. NSDUH also reports on substance use disorders, substance use treatment, mental health problems, and mental health care.


NSDUH is representative of people aged 12 years and over in the civilian noninstitutionalized population of the United States, and in each state and the District of Columbia (D.C.).

The survey covers residents of households (including those living in houses, townhouses, apartments, and condominiums), people in noninstitutional group quarters (including those in shelters, boardinghouses, college dormitories, migratory work camps, and halfway houses), and civilians living on military bases. People excluded from the survey include people experiencing homelessness who do not use shelters, active military personnel, and residents of institutional group quarters such as jails, nursing homes, mental institutions, and long-term care hospitals.


Data are collected via in-person interviews conducted with a sample of individuals at their place of residence. Computer-assisted interviewing methods, including audio computer-assisted self-interviewing, are used to provide a private and confidential setting to complete the interview.

The NSDUH sample design is revised periodically. In 2014, NSDUH introduced an independent multistage area probability sample within each state and D.C. States are the first level of stratification, and each state is then stratified into approximately equally populated state sampling regions (SSRs). Census tracts within each SSR are then selected, followed by census block groups within census tracts, and then area segments (that is, a collection of census blocks) within census block groups. Finally, dwelling units (DUs) are selected within segments, and within each selected DU, up to two residents who are at least 12 years old are selected for the interview.

Also starting in 2014, changes were made in the sample sizes allocated to each state and to different age groups to increase the precision of national estimates, many state estimates, and estimates for older adults. States with sample increases have more precise estimates than in previous years, whereas states with smaller sample sizes have some reductions in precision. However, all states still have reasonable levels of precision. This allocation of sample to states is also thought to be more cost-efficient. Starting in 2014, the sample size was redistributed by age group so that 25% of the sample is allocated to those aged 12–17 years, 25% to those aged 18–25, and 50% to those aged 26 and over. Although the sample sizes for age groups 12–17 years and 18–25 were reduced, these two groups are still considered to be oversampled because they represent about 10% and 13% of the total population, respectively.

Sample Size and Response Rate

In 2019, screening was completed at 148,023 addresses, and 67,625 interviews were completed, including 16,894 interviews from adolescents aged 12–17 years and 50,731 interviews from adults aged 18 and over. Weighted response rates for household screening and for interviewing were 70.5% and 64.9%, respectively, for an overall weighted response rate of 45.8% for people aged 12 years and over.

Issues Affecting Interpretation

Several improvements have been made to NSDUH over time. The data collected in 2002 represent a new baseline for tracking trends in substance use and other measures. Special questions on methamphetamine were added in 2005 and 2006. Data for years before 2007 were adjusted for comparability. Starting with 2011 data, U.S. Census 2010-based control totals were used in the weighting process. Analysis weights in the 2002–2010 NSDUHs were derived from U.S. Census 2000 data. This reweighting to the 2010 census data could affect comparisons between estimates for 2011 with those from both prior and subsequent years. However, an analysis of the impact of reweighting showed that the percentages of substance users were largely unaffected. For more information, see:

The NSDUH questionnaire underwent a partial redesign in 2015 to improve the quality of data and address the changing needs of policy makers and researchers regarding substance use and mental health issues. Due to the changes, only 2015–2019 data are presented for certain estimates until comparability with earlier years can be established. Trends continue to be presented for estimates that are assumed to have remained comparable with those in earlier years. For more information, see:

Estimates of substance use for youth based on NSDUH are not directly comparable with estimates based on the Monitoring the Future (MTF) Study. Rates are not directly comparable across these surveys because of differences in populations covered, sample design, questionnaires, and interview setting. NSDUH collects data in residences, whereas MTF collects data in school classrooms. Furthermore, NSDUH estimates are tabulated by age, whereas MTF estimates are tabulated by grade, representing different ages as well as different populations.



For more information, see the NSDUH website at:, and the Center for Behavioral Health Statistics and Quality (data collection agency) website at: