Table of Contents  |  Search Technical Documentation  |  References

NAEP Sample Design → NAEP 2003 Sample Design → 2003 National Main Assessment Sample Design → Sampling of Schools for the 2003 National Main Assessment → Fourth- and Eighth-Grade Public School Selection for the 2003 National Main Assessment

NAEP Technical DocumentationFourth- and Eighth-Grade Public School Selection for the 2003 National Main Assessment

In general, grades 4 and 8 public school samples selected for the state assessment were also used for the national main assessment. Similarly, the student assessments for the state study were all used for the national main assessment. The Bureau of Indian Affairs schools declined to participate in the state assessment. Albuquerque, New Mexico declined participation in the Trial Urban District Assessment (TUDA) study but did participate in the New Mexico state assessment. In these cases, the national main sample used a subsample of schools drawn from the jurisdiction samples.

The process for drawing subsamples includes computing appropriate school probabilities of selection using the national main sampling rates for the jurisdictions (as if no state samples had been drawn). These probabilities are then divided by the State NAEP probabilities to obtain conditional probabilities of selection for subsampling (in all cases these measures of size were less than or equal to 1). School samples were drawn using the conditional probabilities. The resultant unconditional probabilities of selection for the subsample of schools are equal to the appropriate values for a stand-alone national main sample. This procedure was also applied to the new-school sample.

Since the subsampling rates were developed before it was known exactly which states and jurisdictions would participate in the state program, subsamples were established for all states. The sampling rate for the national main subsample was set at 1.3 percent, and the sampling parameters for the subsamples were adjusted to achieve this overall rate. The probability of selection for a school depended on the school's measure of size and its proportionality constant. Since the measure of size for a school was based on grade enrollment, which, for purposes of sampling, was held constant, the proportionality constants (b_j ) were adjusted to obtain the appropriate number of schools for the national main subsample. The following table provides the proportionality constants for selecting the national main subsamples by grade and jurisdiction.

Public school sample proportionality constants, jurisdiction, national main assessment, by grade: 2003

Grade	Jurisdiction	Proportionality constant bj
4	District of Columbia	0.0002443
	Bureau of Indian Affairs	0.0002335
	DDESS1	0.0007151
	All other jurisdictions	0.0002113
8	District of Columbia	0.0004491
	Bureau of Indian Affairs	0.0002681
	DDESS1	0.0015244
	All other jurisdictions	0.0002312
1 Department of Defense Domestic Dependent Elementary and Secondary Schools. SOURCE: U.S. Department of Education, Institute of Education Sciences, National Center for Education Statistics, National Assessment of Educational Progress (NAEP), 2003.

Printer-friendly Version