The private school sample (the "delta sample") was designed to produce a nationally representative school and student sample for all of the studies (operational, bridge, and pilot) among the students in private schools in the United States.
For each grade, private schools were divided into four strata based on school affiliation, and implicitly stratified within the four explicit strata. The table below shows target sample sizes for the student assessments for each assessment type (operational, science bridge, pilot), by private school stratum (Catholic, Lutheran, Conservative Christian, and other private), and overall, for fourth, eighth, and twelfth grades, respectively.
The design called for oversampling of specific private school groups for those assessments where state participation is required - namely grade 4 and grade 8 reading and mathematics. Consequently the private school samples for those assessments are much larger than for science and for grade 12.
Target sample sizes were adjusted for expected school and student response and eligibility.
|Total fourth grade||16,040||8,025||1,693||2,107||4,215|
|Total eighth grade||16,090||8,050||1,696||2,114||4,230|
|Total twelfth grade||9,550||4,775||477||1,433||2,865|
|SOURCE: U.S. Department of Education, Institute of Education Sciences, National Center for Education Statistics, National Assessment of Educational Progress (NAEP), 2005.|
Samples were based on a two-stage design that involved selection of schools within strata and selection of students within schools. The first-stage samples of schools were selected with probability proportional to a measure of size based on the estimated grade-specific enrollment in the schools.