NAEP Assessment Weighting Procedures → Weighting Procedures for the 2008 Assessment → Weighting Procedures for the 2008 Arts Assessment → Computation of Full-Sample Weights for the 2008 Arts Assessment → School and Student Nonresponse Adjustments for the 2008 Arts Assessment → School Nonresponse Adjustment for the 2008 Arts Assessment → Development of Final School Nonresponse Cells for the 2008 Arts Assessment

NAEP Technical DocumentationDevelopment of Final School Nonresponse Cells for the 2008 Arts Assessment

Limits were placed on the magnitude of cell sizes and adjustment factors to prevent unstable nonresponse adjustments and unacceptably large nonresponse factors. All initial weighting cells with fewer than six cooperating schools or adjustment factors greater than 3.0 were combined with suitable adjacent cells. Simultaneously, all initial weighting cells for any replicate with fewer than four cooperating schools or adjustment factors greater than 3.0 (or 2 times the full sample nonresponse adjustment factor, if greater than 3.0) were combined with suitable adjacent cells. Initial weighting cells were generally combined in reverse order of the cell structure; that is, starting at the bottom of the nesting structure and working up towards the top level of the nesting structure.

For the public school samples, race/ethnicity classification cells within a given census region and urbanicity (defined by locale variable) stratum were combined first. When further combining was required, cells with the most similar urbanicity strata were combined. Combining did not occur across census region.

For the private school samples, race/ethnicity classification cells within a given census region and affiliation (Catholic or non-Catholic) were combined first. When further combining was required, cells were combined across affiliation within census region. Combining did not occur across census region.

Printer-friendly Version