Skip Navigation

Table of Contents  |  Search Technical Documentation  |  References

Trimming of Student Weights in State Samples

Student weights that are much larger than the median weight for a particular jurisdiction will produce sample estimates which have a higher variance  (see, for example, Kish (1992)). The general procedure in the 2002 state assessment trimmed those weights that were greater than 3.5 times the median weight value. Although introducing some bias, trimming weights results in a lower overall mean square error, given the reduction in variance.

The trimming groups were defined as unique jurisdictions, except for the five states with Trial Urban District Assessment (TUDA) districts. For these five states, the TUDA part and non-TUDA part were the two trimming groups. The procedure computed the median of the nonresponse-adjusted student weights in the trimming group. Any weight that was more than 3.5 times the median received a trimming factor:

TRIM subscript s k equals open left bracket 3.5 times M subscript g divided by STUWGT subscript s k times STNRADJ subscript d if STUWGT subscript s k times STNRADJ subscript d is greater than 3.5 times M subscript g or 1 if otherwise

where

  • Mg is the median of the nonresponse-adjusted student weights in trimming group g;
  • STUWGTsk is the student base weight for student k in school s; and
  • STNRADJd is the student nonresponse adjustment for adjustment cell d.

It should be noted that ineligible students were not included in the calculation of the median.


Last updated 06 November 2008 (RF)

Printer-friendly Version