Table of Contents  |  Search Technical Documentation  |  References

NAEP Weighting Procedures → Weighting Procedures for the 2000 State Assessment → Weighting of New Schools

NAEP Technical DocumentationWeighting of New Schools

			New Schools in the 2000 Assessment

New public schools include recently opened schools not listed on the original sampling frame; and schools existing on the sampling frame that changed grade spans to include an eligible grade. It is important to include these schools in the sample so that all eligible students have a chance of selection for NAEP.

New schools are identified and sampled through a two-stage sampling process, involving the selection of districts, and then of new schools within selected districts. There are two distinct processes used depending upon the size of the district.

In the selection of new public schools within each jurisdiction, public school districts are partitioned into "small" districts—those having at most three schools on the sampling frame and no more than one school at each of grades 4, 8, and 12. The remainder of the districts were denoted as "large" districts (i.e., those having multiple schools in at least one of grades 4 or 8), a sample of districts is selected in each jurisdiction. Districts in the sample are asked to identify schools having grade 4 or grade 8 that were not included on the school frame. A sample of these newly identified schools is then selected. The base weight for these schools reflect the probability of two factors:

• that the district was selected for this updating process and

• that the school was included in the NAEP sample, having been identified as new by the district.

If a school has grade 8 but is only large enough to assess one subject, the base weight includes a factor of 2. In 2000, there was one such school identified in a small district.

The base weights for new schools are then evaluated for possible trimming. The process involves computing a hypothetical school base weight for the new schools as though they had been selected as part of the original sample. The hypothetical base weight is then compared to the actual base weight. Those schools with actual base weights greater than three times the hypothetical base weights have their base weights trimmed to three times their hypothetical base weights.

The trimming factor is computed as

where RSCHBWT denotes the ratio of the school base weight to the hypothetical base weight.

The trimmed school base weight, denoted by , is then defined as

= ×

where

•  equals the school base weight and

•  equals the trimming factor.

Printer-friendly Version