Table of Contents | Search Technical Documentation | References
Weight trimming usually occurs for new schools (all new schools are public) and private schools that contributed too much to the mean square error. In 2004, no new schools were introduced into the sample. For this reason, the public school weights were not considered for trimming.
Private schools eligible for trimming were Private School Survey (PSS) nonrespondents who were found subsequently to have larger enrollments than assumed at the time of sampling. To detect extremely large weights among private schools, a comparison was made between a private school's school base weight and its ideal weight (i.e., the weight that would have resulted had the school been on the PSS frame with accurate enrollment and known affiliation). If the school base weight was more then three times the ideal weight, a trimming factor was calculated for that school. This trimming factor scaled the base weight back to three times the ideal weight. The calculation of the school-level trimming factor for a private school s in jurisdiction j is expressed in the following formula:
where
EXP_WTjs is the ideal base weight the school would have received if it had been on the PSS sampling frame with accurate affiliation and known enrollment, and
SCH_BWTjs is the actual school base weight the school received as a sampled private school.