Item Characteristic Curve Asymmetry: A Better Way to Accommodate Slips and Guesses than a Four-Parameter Model?

Autor/inn/en	Liao, Xiangyi; Bolt, Daniel M.
Titel	Item Characteristic Curve Asymmetry: A Better Way to Accommodate Slips and Guesses than a Four-Parameter Model?
Quelle	In: Journal of Educational and Behavioral Statistics, 46 (2021) 6, S.753-775 (23 Seiten)Infoseite zur Zeitschrift PDF als Volltext Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	1076-9986
DOI	10.3102/10769986211003283
Schlagwörter	Test Items; Models; Mathematics Tests; Item Response Theory; Multiple Choice Tests; Standardized Tests; Response Style (Tests); Difficulty Level; Achievement Tests; Grade 3; Grade 4; Grade 5; Grade 6; Grade 7; Grade 8; Wisconsin; Wisconsin Knowledge and Concepts Examinations + Suchen Sie Ihr Suchwort? Test content; Testaufgabe; Analogiemodell; Item-Response-Theorie; Multiple choice examinations; Multiple-choice tests, Multiple-choice examinations; Multiple-Choice-Verfahren; Standadised tests; Standardisierter Test; Antwortverhalten; Schwierigkeitsgrad; Achievement test; Achievement; Testing; Test; Tests; Leistungsbeurteilung; Leistungsüberprüfung; Leistung; Testdurchführung; Testen; School year 03; 3. Schuljahr; Schuljahr 03; School year 04; 4. Schuljahr; Schuljahr 04; School year 05; 5. Schuljahr; Schuljahr 05; School year 06; 6. Schuljahr; Schuljahr 06; School year 07; 7. Schuljahr; Schuljahr 07; School year 08; 8. Schuljahr; Schuljahr 08
Abstract	Four-parameter models have received increasing psychometric attention in recent years, as a reduced upper asymptote for item characteristic curves can be appealing for measurement applications such as adaptive testing and person-fit assessment. However, applications can be challenging due to the large number of parameters in the model. In this article, we demonstrate in the context of mathematics assessments how the slip and guess parameters of a four-parameter model may often be empirically related. This observation also has a psychological explanation to the extent that both asymptote parameters may be manifestations of a single item complexity characteristic. The relationship between lower and upper asymptotes motivates the consideration of an asymmetric item response theory model as a three-parameter alternative to the four-parameter model. Using actual response data from mathematics multiple-choice tests, we demonstrate the empirical superiority of a three-parameter asymmetric model in several standardized tests of mathematics. To the extent that a model of asymmetry ultimately portrays slips and guesses not as purely random but rather as proficiency-related phenomena, we argue that the asymmetric approach may also have greater psychological plausibility. (As Provided).
Anmerkungen	SAGE Publications. 2455 Teller Road, Thousand Oaks, CA 91320. Tel: 800-818-7243; Tel: 805-499-9774; Fax: 800-583-2665; e-mail: journals@sagepub.com; Web site: http://sagepub.com
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01