Multistage area probability sample design involving three
selection stages: (1) geographic areas or primary sampling units
(PSUs), (2) schools (or linked groups of schools) within PSUs, and (3)
students within sampled schools. Of the 80 PSUs, 8 were selected with
certainty and 72 were selected with probability proportionate to size
based on the size of the senior class. In schools with more than 400
seniors, a random sample of seniors or classes was drawn. In schools
with less than 400 seniors, all seniors were asked to participate.
Each school was asked to participate for two years so that each year
one-half of the sample is replaced. Schools refusing participation
were replaced with similar schools in terms of geographic location,
size, and type of school (e.g., public, private/Catholic,
private/non-Catholic). The total sample was divided into six
subsamples consisting of an average of 2,700 respondents, and each
subsample was administered a different form of the questionnaire,
although all respondents answered the "core" drug and demographic
High school seniors in the contiguous United States.
The participation rate among schools has been
between 66 and 80 percent since the inception of the study. The
overall student response rate for 1995 was 84 percent.