Evaluation of April 1, 2000 School District Population Estimates Based on the Synthetic Ratio Method. Population Division Working Papaer No. 74

摘要

The Department of Education uses school district population estimates in combination with estimates of the numbers of children in poverty to distribute billions of dollars in federal funds to school districts. This report evaluates the synthetic ratio method used to produce postcensal school district estimates of the total population and the school-age population (5 to 17 years). The synthetic ratio method assumes that the ratio of the school district population to the county population, as measured in the most recent decennial census, remains constant throughout the estimate period. To evaluate the method, school district population estimates for April 1, 2000 are produced from the 1990 census population of school districts and counties and the April 1, 2000 county population estimates. The accuracy of the April 1, 2000 estimates is measured by comparison with Census 2000 enumeration data. The Mean Algebraic Percent Error (MALPE), the Mean Absolute Percent Error (MAPE), and the Weighted Mean Absolute Percent Error are calculated for the school district population estimates. The average errors are calculated for regions, states, school district types, school district population size in 1990 and 2000, and the percent population change from 1990 to 2000. The results identify the characteristics of school districts for which the synthetic ratio method performs relatively well and for which the method appears to generate biased estimates.