Table of Contents  |  Search Technical Documentation  |  References

NAEP Technical DocumentationNAEP 2007 Sample Design

			2007 State Assessment Sample Design 2007 National Assessment Sample Design

In 2007 representative samples were drawn for the following operational and pilot assessments:

• national assessments of students in public and private schools in reading and mathematics at grades 4 and 8, and writing at grades 8 and 12;

• state-by-state and Trial Urban District Assessment (TUDA) in reading and mathematics for public schools at grades 4 and 8, and writing at grade 8; and
• pilot tests in reading and mathematics in public and private schools at grades 4 and 8, and reading in grade 12 public schools.

Representative samples were drawn for three separate components:

• reading, mathematics, and writing assessments of fourth- and eighth-grade students in public schools (the alpha sample);

• writing assessments of twelfth-grade students in public schools (the gamma sample); and
• reading and mathematics assessments of fourth- and eighth-grade students and writing assessments of eighth- and twelfth-grade students in private schools (the delta sample).

The national assessment was designed to achieve a nationally representative sample of public and private school students in the fourth, eighth, and twelfth grades. Its target population included all students in public and private schools, including Bureau of Indian Education (BIE) and Department of Defense Domestic Dependent Elementary and Secondary Schools (DDESS), who were enrolled in fourth, eighth, and twelfth grades at the time of assessment.

For fourth- and eighth-grade public schools, the NAEP state student samples and assessments account for the NAEP national main student samples and assessments. Nationally representative samples were drawn for the remaining populations: public school students in twelfth grade and private school students in fourth, eighth, and twelfth grades. In state samples, a small portion of students received the writing assessment in states not participating in writing to supplement the national writing sample.

The TUDA samples formed part of the corresponding state public school samples, and the state samples formed the public school grades 4 and 8 part of the national sample.

The selected samples were based on a two-stage sample design:

• 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.

The state assessment examined fourth- and eighth-grade students in public schools. A representative sample of public school students was drawn in each participating jurisdiction, which included states, District of Columbia, Puerto Rico, BIE schools, Department of Defense Dependents Schools (DODDS), and school districts chosen for the TUDA study. Each sample was designed to produce aggregate estimates with approximately equal precision for all the participating jurisdictions, as well as estimates for various student subpopulations of interest.

School participation in the mathematics and reading assessments at the state level was mandatory, whereas participation in the writing study was optional, with five states and the District of Columbia declining to participate. By design, Puerto Rico participated only in mathematics and BIE participated only in reading and mathematics at the state level.

Sample sizes were expanded in three large states (California, Florida, and Texas) in recognition of their diverse populations because increased sample sizes permit meaningful breakdowns of the results at finer levels. Applying increases in these large states also significantly improves the precision of national estimates, both overall and by demographic subgroups.

Since charter schools were reported as a separate reporting group, those in California, Texas, and New York were oversampled at grades 4 and 8, though not in the corresponding TUDA districts in these states.

All BIE schools were included in the sample. Also, schools with high American Indian populations were oversampled in six states (Washington, Oregon, Arizona, North Carolina, Minnesota, and Michigan). This was designed to enhance the reporting of results for American Indian students at the state level in those states with a sizable proportion of the nation's American Indian students for the National Indian Education Study (NIES), which was conducted in conjunction with NAEP.

The Trends in International Mathematics and Science Study (TIMSS) was being conducted in the same time period as NAEP. Overlap between schools in the NAEP samples and the TIMSS samples was minimized in grades 4 and 8 schools, public and private.

The figure below illustrates the various sample types and subjects.

Components of the NAEP 2007 samples, by assessment subject, school type, and grade: 2007

† Not applicable.
NOTE: View an accessible version of this figure.
SOURCE: U.S. Department of Education, Institute of Education Sciences, National Center for Education Statistics, National Assessment of Educational Progress (NAEP), 2007.

Printer-friendly Version