U.S. flag

An official website of the United States government

Skip Header

Weighting Change for the School Enrollment Supplement to the Current Population Survey

Executive Summary

In reviewing the October 2006 Current Population Survey (CPS) School Enrollment Supplement data, representatives from the Housing and Household Economic Statistics Division (HHES) noticed the CPS estimate for the number of people receiving a high school diploma or General Education Diploma (GED) in the current survey year was lower than an administrative records estimate provided by the National Center for Education Statistics (NCES). The Housing and Household Economic Statistics Division (HHES), in conjunction with the Demographic Surveys Division (DSD) and the Demographic Statistical Methods Division (DSMD), believed the revised CPS weighting plan implemented in 2003 could have affected the high school completion estimate. The weighting plan implemented in 2003 included less detailed age group breakouts in the second-stage weighting adjustment.

To evaluate the effect this weighting change had on the high school completion estimate, DSD calculated October 2006 high school completion estimates using both the current weighting plan and a new weighting plan with an additional weighting step using detailed controls for 16-19 year olds. These estimates were then compared against each other and against the administrative records estimate provided by NCES. The new CPS weight variable resulted in an estimate of high school graduates in 2006 that was larger than the estimate produced by the current CPS weight variable. Despite this increase, the new estimate was still statistically smaller than the administrative records estimate from NCES. However, in looking carefully at the difference between the estimates, HHES determined that this change to the weighting plan was the only justifiable correction that would address this problem. The remainder of the difference between the NCES estimate and the CPS estimate using the new weighting plan may be the result of differences in either the data collection system, or of differences between the systems that are relatively subtle, but not "problems" per se. Representatives from DSD, DSMD, and HHES recommended that the new weighting adjustment should be included into the standard School Enrollment Supplement weighting process beginning in October 2007.


Back to Header