Multistage area probability sample design involving five
selection stages: (1) primary sampling units areas (e.g., counties), (2) subareas within primary areas (e.g., blocks or block groups), (3) listing units within subareas, (4) domains within sampled listing units, and (5) eligible individuals within sampled domains. A total of
115 Primary Sampling Units (PSUs), including areas of high Hispanic concentration, were selected to represent the total United States population. These PSUs were defined as metropolitan areas, counties, groups of counties, and independent cities. Of the 115 PSUs, 43 were selected with certainty and 72 were randomly selected with probability
proportional to size. Unlike the previous NHSDAs, the 1996 NHSDA did not oversample cigarette smokers aged 18-34. A design feature of the 1996 NHSDA is the overlap with segments previously surveyed in the 1995 NHSDA. About 95 percent of 1995 sample segments were screened again in 1996 to identify and sample occupied dwelling units in these
segments that had not previously been interviewed in the 1995 NHSDA. The reuse of 1995 NHSDA segments reduced the overall costs of counting and listing dwelling units in the 1996 NHSDA and also modestly increased the precision of comparisons between the 1995 and 1996 NHSDAs. The five age groups were: ages 12-17, 18-25, 26-34, 35-49, and 50 and
older. The three race/ethnic groups were: Whites/others, Blacks, and Hispanics. Blacks and Hispanics were oversampled. The study yielded an 84.9 percent eligibility rate for sample households and a 92.7 percent completion rate for screening eligible households.
The civilian, noninstitutionalized population of the
United States aged 12 and older, including residents of
noninstitutional group quarters, such as college dormitories, group
homes, shelters, rooming houses, and civilians dwelling on military
personal interviews and self-enumerated answer sheets
The interview response rates for the three racial/ethnic groups were: 77.1 percent for Whites/others, 79.4 percent for Blacks, and 80.9 percent for Hispanics. The overall unweighted interview response rate was 78.6 percent. A completed interview had to contain, at a minimum, data on the recency
of use of marijuana, cocaine, and alcohol.