Sample Size and Item Parameter Estimation Precision When Utilizing the Masters' Partial Credit Model

Autor/inn/en	Custer, Michael; Kim, Jongpil
Titel	Sample Size and Item Parameter Estimation Precision When Utilizing the Masters' Partial Credit Model
Quelle	(2023), (13 Seiten) PDF als Volltext kostenfreie Datei Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
Schlagwörter	Sample Size; Item Response Theory; Test Items; Computation; Models; Error of Measurement; Scores; Generalizability Theory; Accuracy; Difficulty Level + Suchen Sie Ihr Suchwort? Item-Response-Theorie; Test content; Testaufgabe; Analogiemodell; Messfehler; Schwierigkeitsgrad
Abstract	This study utilizes an analysis of diminishing returns to examine the relationship between sample size and item parameter estimation precision when utilizing the Masters' Partial Credit Model for polytomous items. Item data from the standardization of the Batelle Developmental Inventory, 3rd Edition were used. Each item was scored with a "0" for no credit, a "1" for partial credit and a "2" for full credit. Two conditions were studied; the first used 40 items and the second 20 items. Item parameter estimates were examined relative to their "true" values by evaluating the decline in root mean squared error (RMSE) and the number of outliers as the level of sample size increased. The generalizability of these results may be limited due to this study's range of item score points, the number of items, and the range of the underlying scale. However, under both conditions, the majority of RMSE and outlier-reduction improvement was achieved once a sample size of 900 examinees had been reached. Diminishing returns were most notable with incremental increases to sample size beyond 1,000 examinees. Practitioners often encounter great variability in the number of items, item types, the number of item score points, the range of an assessment's underlying scale and the stakes associated with calibration objectives. Given this variability, practitioners might be encouraged to first simulate item data and vary the level of sample size to evaluate estimation precision across the scale through a similar review of RMSE and "outliers" as the level of sample size increases. Besides the consideration of sample acquisition costs, an evaluation of "diminishing returns" could aid practitioners in their selection of an appropriate sample size. (As Provided).
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01