ERIC Number: ED040406
Record Type: RIE
Publication Date: 1970-Mar
Reference Count: 0
Using Performance Data Gathered at Several Stages of Achievement in Predicting Subsequent Performance.
Owen, Steven V.; Feldhusen, John F.
This study compares the effectiveness of three models of multivariate prediction for academic success in identifying the criterion variance of achievement in nursing education. The first model involves the use of an optimum set of predictors and one equation derived from a regression analysis on first semester grade average in predicting the subsequent semester indices. In the second model, an optimum set of predictors and a new equation are derived for each semester average, individually. For the third model, each semester's optimum set and equation are determined individually, but prior semester averages are not included. In the first model predictive efficiency declines sharply from semester to semester. The second model predictions remained stable over the four semesters. Statistical comparison between the second and third models shows that the inclusion of prior semester averages in the prediction battery strongly increased the predictive efficiency beyond that level attained for each sample's first semester average. (Author/MC)
Publication Type: N/A
Education Level: N/A
Authoring Institution: National Council on Measurement in Education, East Lansing, MI.; Purdue Univ., Lafayette, IN.
Note: Paper presented at the annual meeting of the National Council on Measurement in Education, Minneapolis, Minnesota, March, 1970