Table of Contents  |  Search Technical Documentation  |  References

NAEP Weighting Procedures → Weighting Procedures for the 2000 State Assessment → School-Level Nonresponse Adjustment Classes

NAEP Technical DocumentationSchool-Level Nonresponse Adjustment Classes

			Construction of the Final Nonresponse Adjustment Classes School Nonresponse Adjustment Factors

The first factor used to adjust the base weight for a student is to take into account nonparticipating schools for which there is no participating substitute. School-level nonresponse adjustment classes are created within each jurisdiction for the 2000 state assessment. For each set, these classes were defined as a function of the following sampling strata:

• minority enrollment,
• urbanicity,
• achievement data, and
• household median income.

For each jurisdiction, except American Samoa, Department of Defense Domestic Dependent Elementary and Secondary Schools (DDESS), Guam, Virgin Islands, and DoDEA Overseas (DoDDS), the initial school nonresponse adjustment cells were formed by crossing urbanicity and minority status. Where there was only one minority status category within a particular level of urbanicity, urbanicity and a categorized version of achievement or median income were crossed instead. For this purpose within each level of urbanization, schools were sorted by the median household income or achievement, and then divided into three groups of about equal size, representing low, middle, and high income (or achievement) areas. Achievement data was used if available, otherwise, median income was used.

For American Samoa, due to the lack of data on urbanicity, achievement, income, and minority classifications, schools were grouped according to enrollment. For DoDEA/DoDDS Domestic, there was no information on minority status, therefore, schools were grouped according to urbanicity and achievement/income classifications. For Guam and Virgin Islands, there was no information on achievement/income. Therefore, in grade 4, Guam and Virgin Island schools were grouped according to minority classifications. In grade 8, due to the low number of schools, Guam and Virgin Island schools were placed in one cell for each jurisdiction.

For the DoDEA Overseas (DoDDS) schools, urbanization, median income, achievement and minority status were not available. Therefore, the initial school nonresponse adjustment classes were defined by the district code.

For variance estimation purposes, separate files were created for jurisdictions with certainty schools having SD/LEP students. In these SD/LEP files, the initial school nonresponse cells were formed as described above.

Printer-friendly Version