Processing of Race and Ethnicity in the National Survey on Drug Use and Health
Grau, E. A., Grau, E. A., Martin, P., Frechtel, P. A., Snodgrass, J. A., & Caspar, R. A. (2005, August). Processing of Race and Ethnicity in the National Survey on Drug Use and Health. Presented at Joint Statistical Meetings, Minneapolis, MN.
Since the inception of the National Household Survey on Drug Abuse (NHSDA), renamed the National Survey on Drug Use and Health (NSDUH) in 2002, questions have been included to determine the race and ethnicity of each respondent. Race and ethnicity are routinely used as part of the demographic breakdowns in the analyses and the various reports generated from the survey. The race and ethnicity categories were updated from previous surveys in 1999 and 2003 pursuant to new Office of Management and Budget (OMB) directives. This paper gives details on the methods used to process the variables associated with race and ethnicity in the NSDUH. Particular emphasis is placed on the methods used to edit and impute these variables. Strategies are outlined for incorporating information from several race and ethnicity questions, and for dealing with interviewer-entered alphanumeric responses. The imputation method used, Predictive Mean Neighborhoods (PMN), was developed specifically for the NSDUH. This paper gives a brief description of the method, which is a combination of predictive mean matching and a random nearest neighbor hot deck, and its application to race and ethnicity variables.