Predictive mean neighborhood imputation for NHSDA substance use data
In previous years, imputation of missing values in the National Household Survey of Drug Abuse (NHSDA) had been accomplished with an unweighted sequential hot deck procedure. In the spirit of improving the quality of estimates from the redesigned NHSDA , there was a need to change the way missing data were edited and imputed. The implementation of the "flag and impute" editing rule, described in Chapter 5, and the desire to impute more variables required a new method that was rigorous, flexible, and preferably multivariate. This chapter presents a new imputation method with these characteristics, termed Predictive Mean Neighborhoods (PMN), that is now being used to impute missing values for NHSDA substance-use variables.