PDF pending restoration
ERIC Number: ED187747
Record Type: RIE
Publication Date: 1980-Apr
Reference Count: 0
An Application of Bayesian M-Group Regression to Developmental Studies Programs in a Community College.
Hinkle, Dennis E.; Polhamus, Edward C.
Classical multiple regression was compared with Bayesian m-group regression, complete with cross-validation. The setting was a post-developmental studies situation in a comprehensive community college. A secondary purpose of the study was to incorporate an advisor prediction of grade point average (GPA) as input into both regression procedures. The reliability and predictive validity of the advisor predictions were both investigated. One major strength of the study was the inclusion of variables measuring progress during developmental studies. Predictions based solely on data available prior to developmental studies would invariably predict failure because it is those variables which suggested a need for developmental studies in the first place. A second major strength of this study was the inclusion of an advisor prediction as a variable in both regression methods. This inclusion maintained comparability between methods while allowing the inclusion of both "hard" and "soft" data. The criterion variable in the study was first-quarter GPA in the student's chosen curriculum, after the student had completed developmental studies. (Author/CTM)
Publication Type: Speeches/Meeting Papers; Reports - Research
Education Level: N/A
Authoring Institution: N/A
Note: Paper presented at the Annual Meeting of the American Educational Research Association (64th, Boston, MA, April 7-11, 1980).