NotesFAQContact Us
Search Tips
ERIC Number: ED048353
Record Type: RIE
Publication Date: 1971-Feb
Pages: 9
Abstractor: N/A
Reference Count: 0
Multiple Regression Prediction Models in the Behavioral Sciences: Prediction of Federal Aid Allocations to Local School Districts.
Gustafson, Richard A.
Twenty-nine community characteristics were studied to determine which were statistically most useful as predictors of per-pupil Federal aid to the 169 school districts of Connecticut. Three regression models were developed using community traits as predictors of Federal aid allocations. Cross-validation of regression models to predict future per-pupil Federal aid allocations introduced a number of problems which were generalizable to other research situations in psychology and measurement. Improving cross-validation of regression models by using restricted models, equating the means of vectors by using constants as multipliers, and examination of standard errors are discussed. Data was analyzed using these three techniques and results compared to those obtained from the traditional cross validation procedures. Implications of these findings are discussed in terms of improving predictive models in measurement and psychological research. See TM 000 419 for a report of the output of the regression models. (Author/LR)
Publication Type: N/A
Education Level: N/A
Audience: N/A
Language: N/A
Sponsor: N/A
Authoring Institution: N/A
Note: Paper presented at the Annual Meeting of the American Educational Research Association, New York, New York, February 4-7, 1971