The 2005 sample design met the following objectives:
These objectives were met by designing four separate sample components:
The TUDA samples formed part of the corresponding state samples, and the state samples formed part of the national sample.
The selected samples were based on a two-stage sample design:
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, Bureau of Indian Affairs (BIA) schools, Department of Defense schools, and school districts chosen for the Trial Urban District Assessment 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 populations of interest. The exception is the BIA jurisdiction, which was not designed to produce jurisdiction-level estimates, but only to contribute to the national estimates.
Participation in the mathematics and reading assessments at the state level was mandatory, whereas participation in the science study was optional, with eight states declining to participate. By design, Puerto Rico participated only in mathematics and BIA schools participated only in reading and mathematics.
Sample sizes were increased in four large states in recognition of their diverse populations because increased sample sizes permit meaningful breakdowns of the results at finer levels than in the past. Applying increases in these large states also significantly improves the precision of national estimates, both overall and by demographic subgroups.
For the reading and mathematics assessments, there was a larger sample of BIA schools. 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 Survey (NIES), which was conducted in conjunction with NAEP.
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 BIA and Department of Defense-Domestic 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, private school students in fourth, eighth, and twelfth grades. For science in public school grades 4 and 8, a supplemental sample was drawn to represent the eight states that declined participation at the state level.
The figure below demonstrates the various sample types and subjects.
Components of the samples, national main and state assessments, by subject area, school type, and grade: 2005