Substate Estimates of Substance Use and Mental Illness from the 2018-2020 NSDUH: Results and Detailed Tables
Substate estimates for these years are no longer available due to methodological concerns with combining 2020 data with data from 2018 and 2019. We apologize for any inconvenience or confusion this may cause.
To protect the safety of field staff and survey participants during the COVID-19 pandemic, SAMHSA decided to suspend in-person NSDUH data collection on March 16, 2020. To reduce the impact of the COVID-19 pandemic on NSDUH data, SAMHSA approved the addition of web-based data collection, and in Quarter 4 of 2020 (i.e., October to December), it became the primary forms of NSDUH data collection. Conventional in-person data collection was carried out wherever it was considered safe to do so based on county- and state-level COVID-19 metrics; however, in the fourth quarter of 2020, most respondents answered the survey via the web. Because of the various demographic groups participating in the survey, and the fact that individuals approach the questions differently depending on the context of the question, it is known that people may respond to the survey differently while taking it in-person versus online. Thus, introducing what is called a mode effect.
The potential for a mode effect to affect comparisons and trends between 2018 and 2020 was known when the state estimates were published. However, the initial assumption was that the mode effect was similar for different groups of people, so calculating the average across 2018-2020 would produce statistically valid results. Further analyses that included data from the 2021 NSDUH has shown that this assumption cannot be made. Because of these analyses, along with concerns about the rapid societal changes in 2020, it was determined that averages across the three years maybe misleading. Therefore, as explained above, the substate estimates for 2018-2020 are no longer provided.