Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Moderator Subgroups and Bayesian m-Group Regression: Some Further Comments:

Moderator Subgroups and Bayesian m-Group Regression: Some Further Comments: American Educational Research Journal Winter 1974, Vol. 11, No. 1, Pp. 87-90 Moderator Subgroups and Bayesian m-Group Regression: Some Further Comments LYLE F . SCHOENFELDT ROBERT W. LISSITZ University of Georgia In our initial paper (Lissitz & Schoenfeldt, 1974), we compared the effectiveness of five moderator subgroup models, including two least square procedures, two probability weighting (semi-Bayesian) methods, and the Bayesian m-group regression method (Novick, Jackson, Thayer, & Cole, 1972), in predicting college grade point average. It was found that the semi- Bayesian, the Bayesian, and within group least squares procedures offered no improvement over the simpler total group least squares method. The Novick and Jackson (1974) reply was concerned with the Bayesian model as it relates to the "classical" (total group least squares) procedure, but focused on the Lissitz and Schoenfeldt (1974) conclusion that the 10% reduction in mean square error reported by Novick et al. (1972) was due to the comparison of the Bayesian procedure to the least effective model, the within-group least squares method. The purpose of the present paper is to comment further on the arguments advanced by Novick and Jackson (1974), specifically the issues raised relevant to their contentions that the Lissitz and Schoenfeldt http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png American Educational Research Journal SAGE

Moderator Subgroups and Bayesian m-Group Regression: Some Further Comments:

Loading next page...
 
/lp/sage/moderator-subgroups-and-bayesian-m-group-regression-some-further-gvGBvv7ZFH

References (11)

Publisher
SAGE
Copyright
Copyright © 2019 by American Educational Research Association
ISSN
0002-8312
eISSN
1935-1011
DOI
10.3102/00028312011001087
Publisher site
See Article on Publisher Site

Abstract

American Educational Research Journal Winter 1974, Vol. 11, No. 1, Pp. 87-90 Moderator Subgroups and Bayesian m-Group Regression: Some Further Comments LYLE F . SCHOENFELDT ROBERT W. LISSITZ University of Georgia In our initial paper (Lissitz & Schoenfeldt, 1974), we compared the effectiveness of five moderator subgroup models, including two least square procedures, two probability weighting (semi-Bayesian) methods, and the Bayesian m-group regression method (Novick, Jackson, Thayer, & Cole, 1972), in predicting college grade point average. It was found that the semi- Bayesian, the Bayesian, and within group least squares procedures offered no improvement over the simpler total group least squares method. The Novick and Jackson (1974) reply was concerned with the Bayesian model as it relates to the "classical" (total group least squares) procedure, but focused on the Lissitz and Schoenfeldt (1974) conclusion that the 10% reduction in mean square error reported by Novick et al. (1972) was due to the comparison of the Bayesian procedure to the least effective model, the within-group least squares method. The purpose of the present paper is to comment further on the arguments advanced by Novick and Jackson (1974), specifically the issues raised relevant to their contentions that the Lissitz and Schoenfeldt

Journal

American Educational Research JournalSAGE

Published: Nov 23, 2016

There are no references for this article.