Using Evidence-Based Decision Trees Instead of Formulas to Identify At-Risk Readers. REL 2014-036

Autor/inn/en	Koon, Sharon; Petscher, Yaacov; Foorman, Barbara R.
Institution	Regional Educational Laboratory Southeast (ED); National Center for Education Evaluation and Regional Assistance (ED)
Titel	Using Evidence-Based Decision Trees Instead of Formulas to Identify At-Risk Readers. REL 2014-036
Quelle	(2014), (26 Seiten) PDF als Volltext (1); PDF als Volltext kostenfreie Datei (2) Verfügbarkeit
Zusatzinformation	ORCID (Petscher, Yaacov) Weitere Informationen
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
Schlagwörter	At Risk Students; Reading Difficulties; Identification; Reading Comprehension; Classification; Regression (Statistics); Models; Nonparametric Statistics; Comparative Analysis; Elementary School Students; Grade 1; Grade 2; Public Schools; Accuracy; Prediction; Florida; Stanford Achievement Tests + Suchen Sie Ihr Suchwort? Reading difficulty; Leseschwierigkeit; Identifikation; Identifizierung; Leseverstehen; Classification system; Klassifikation; Klassifikationssystem; Regression; Regressionsanalyse; Analogiemodell; School year 01; 1. Schuljahr; Schuljahr 01; School year 02; 2. Schuljahr; Schuljahr 02; Public school; Öffentliche Schule; Vorhersage
Abstract	This study examines whether the classification and regression tree (CART) model improves the early identification of students at risk for reading comprehension difficulties compared with the more difficult to interpret logistic regression model. CART is a type of predictive modeling that relies on nonparametric techniques. It presents results in an easy-to-interpret "tree" format, enabling parents, teachers, principals, and school district leaders to better understand how a student is predicted to be at risk. Using data from a sample of Florida public school students in grades 1 and 2 in 2012/13, the study found that the CART model predicted poor performance on the reading comprehension subtest of the Stanford Achievement Test as accurately as logistic regression while using fewer or the same number of variables. This research is motivated by state education leaders' interest in maintaining high classification accuracy while simultaneously improving practitioner understanding of the rules used to identify students as at-risk or not at-risk readers. An appendix provides detailed information on the study's data sources and methodology. (ERIC).
Anmerkungen	Regional Educational Laboratory Southeast. Available from: Florida Center for Reading Research, Florida State University, 2010 Levy Avenue Suite 100, Tallahassee, FL 32310. Tel: 850-644-9352; e-mail: rel-se@fsu.edu; Web site: http://rel-se.fcrr.org
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2017/4/10