ERIC Number: ED431218
Record Type: Non-Journal
Publication Date: 1999-Apr
Reference Count: N/A
Predicting School Enrollments Using the Modified Regression Technique.
Grip, Richard S.; Young, John W.
This report is based on a study in which a regression model was constructed to increase accuracy in enrollment predictions. A model, known as the Modified Regression Technique (MRT), was used to examine K-12 enrollment over the past 20 years in 2 New Jersey school districts of similar size and ethnicity. To test the model's accuracy, MRT was compared to the Cohort-Survival Ratio method--the most common method employed by school planners--using two prediction time frames, 1990-96 and 1993-96. These time frames were then compared to actual enrollments. The results show that MRT performed significantly better than the Cohort-Survival Ratio, achieving much lower absolute-mean-error rates. Error rates were larger for one of the districts using either method; for most accurate results, both models worked best under conditions of uniform growth or decline. Furthermore, smaller data sets produced the best results, indicating that, rather than picking the greatest number of years available, school planners should use data that closely resembles prevailing trends. It is suggested that MRT can provide school planners with a more accurate methodology for predicting long-term school enrollments, helping them to make decisions regarding the opening and closing of schools, hiring new faculty, and planning time. (RJM)
Publication Type: Reports - Research; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A
Identifiers - Location: New Jersey