A Generalizability Approach To Evaluating the Reliability of Testlet-Based Test Scores.

Autor/inn/en	Lee, Guemin; Frisbie, David A.
Titel	A Generalizability Approach To Evaluating the Reliability of Testlet-Based Test Scores.
Quelle	(1997), (35 Seiten) PDF als Volltext kostenfreie Datei Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
Schlagwörter	Quantitative Daten; Estimation (Mathematics); Generalizability Theory; Reliability; Scores; Tables (Data); Test Items; Test Results + Suchen Sie Ihr Suchwort? Estimation; Mathematics; Schätzung; Reliabilität; Tabelle; Test content; Testaufgabe
Abstract	Previous studies have indicated that the reliability of test scores composed of testlets might be overestimated by conventional item-based reliability estimation methods (R. Thorndike, 1953; A. Anastasi, 1988; S. Sireci, D. Thissen, and H. Wainer, 1991; H. Wainer and D. Thissen, 1996). This study used generalizability theory to investigate the relative adequacy of reliability coefficients from test scores composed of testlets with a p x (I:H) random effects design, where persons are crossed with items nested within passages. The magnitude of overestimation of using Cronbach's coefficient alpha based on item scores in this situation was estimated to be about 0.04. The passage facet turns out to be more influential on reliability estimates than the item-within-passage facet. Given a fixed total number of items and a fixed number of passages, the variability of generalizability coefficients with varying number of items per passage is small (under 0.01). Therefore, manipulating the number of passages is a more productive way to obtain efficient measurement procedures than is manipulating the number of items within each passage. (Contains 7 tables, 3 figures, and 18 references.) (Author)
Erfasst von	ERIC (Education Resources Information Center), Washington, DC