Using Classification Tree Models to Determine Course Placement

Autor/in	Lee, Chansoon
Titel	Using Classification Tree Models to Determine Course Placement
Quelle	In: Educational Measurement: Issues and Practice, 41 (2022) 2, S.82-89 (8 Seiten)Infoseite zur Zeitschrift PDF als Volltext Verfügbarkeit
Zusatzinformation	ORCID (Lee, Chansoon)
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	0731-1745
DOI	10.1111/emip.12470
Schlagwörter	Classification; Models; Student Placement; College Students; Cutting Scores; Algebra; Prediction; Accuracy + Suchen Sie Ihr Suchwort? Classification system; Klassifikation; Klassifikationssystem; Analogiemodell; Schülerpraktikum; Collegestudent; Vorhersage
Abstract	Appropriate placement into courses at postsecondary institutions is critical for the success of students in terms of retention and graduation rates. To reduce the number of students who are misplaced, using multiple measures in placing students is encouraged. However, in practice most postsecondary schools utilize only a few measures to determine course placement. One of the reasons is the lack of research on methodologies that can be used to develop and establish appropriate cutoff scores using multiple measures. The purpose of this study is to investigate whether the classification tree model is a useful alternative approach to the multiple logistic regression model for placement into college courses. For comparison, this research examined the approaches' effectiveness and predictive accuracy for College Algebra. Data were obtained from two medium-sized four year, midwestern institutions. Using two well-known tree models, important measures and their cutoff scores for College Algebra were determined. The findings of this study showed that tree models were an effective alternative approach. Tree models also performed better than, or as well as, the multiple logistic regression model in predictive accuracy. (As Provided).
Anmerkungen	Wiley. Available from: John Wiley & Sons, Inc. 111 River Street, Hoboken, NJ 07030. Tel: 800-835-6770; e-mail: cs-journals@wiley.com; Web site: https://www.wiley.com/en-us
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01