The sample design for the NAEP 2007 study in twelfth-grade public schools (the "gamma" sample) achieved a nationally representative sample of public school students in the twelfth grade through the use of a two-stage approach: selection of schools within strata and selection of students within schools. The first-stage sample of schools was selected with probability proportional to a measure of size based on the estimated grade-specific enrollment in the schools.
The general target for the twelfth-grade public school sample was 18,000 assessed students. The operational study test was in writing. Pilot tests were also included. Target sample sizes were adjusted for expected school and student response and eligibility.
As in past assessments, Black and Hispanic students were oversampled at a moderate rate. Schools in a high Black/Hispanic stratum (schools with 15 percent or more Black and Hispanic students with at least 10 Black or Hispanic students in the twelfth grade) were sampled at twice the rate as those in a low Black/Hispanic stratum to implement oversampling of Black and Hispanic students in the twelfth-grade public school sample.
From the stratified frame of twelfth-grade public schools, a systematic random sample of grade-eligible schools was drawn with probability proportional to a measure of size based on the estimated grade-specific enrollment of the school. Schools with a high enrollment of Black and Hispanic students were sampled at twice the rate by doubling the measure of size.
Each selected school in the twelfth-grade public school sample provided a list of eligible enrolled students from which a systematic, equal probability sample of students was drawn. As many as 78 students were taken with certainty if the number of twelfth-graders was less than or equal to 78, and a sample of 71 was taken in larger schools.