Detecting DIF for Polytomously Scored Items: An Adaptation of the SIBTEST Procedure. Research Report.

Autor/inn/en	Chang, Hua-Hua; und weitere
Institution	Educational Testing Service, Princeton, NJ.
Titel	Detecting DIF for Polytomously Scored Items: An Adaptation of the SIBTEST Procedure. Research Report.
Quelle	(1995), (35 Seiten) PDF als Volltext kostenfreie Datei Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
Schlagwörter	Evaluation Methods; Identification; Item Bias; Robustness (Statistics); Simulation; Test Items + Suchen Sie Ihr Suchwort? Identifikation; Identifizierung; Widerstandsfähigkeit; Simulation program; Simulationsprogramm; Test content; Testaufgabe
Abstract	Recently, R. Shealy and W. Stout (1993) proposed a procedure for detecting differential item functioning (DIF) called SIBTEST. Current versions of SIBTEST can only be used for dichotomously scored items, but this paper presents an extension to handle polytomous items. The paper presents: (1) a discussion of an appropriate definition of DIF for polytomously scored items; (2) a modified SIBTEST procedure for detecting DIF for polytomously scored items; and (3) the results of two simulation studies comparing the modified SIBTEST with the Mantel-Haenszel and standardized mean difference procedures. One study used data constrained by the Rasch-like partial credit model, and the other used data with distinct discriminations across items. The simulations indicate that the methodology of including the studied item in matching subtests for controlling impact-induced Type I error tends to yield Type I and Type II error inflation rates that are highly unacceptable when the equal discrimination condition is violated. They provide evidence that the modified SIBTEST procedure is more robust with regard to controlling impact-induced Type I error rate inflation than the other procedures. (Contains 1 figure, 6 tables, and 26 references.) (Author/SLD)
Erfasst von	ERIC (Education Resources Information Center), Washington, DC