期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2021
卷号：99
期号：4
语种：English
出版社：Journal of Theoretical and Applied
摘要：Efficiency Balanced Information is an item selection method developed by Han (2009) with the aim of this research is to solve problems of other methods that have previously been widely applied in CAT. This study aims to explore the effectiveness of using Efficiency Balanced Information for item selection. This research will identify criteria that affect this method so that it is optimal when used in the CAT to predict student abilities. This research is simulation research with two simulation software, WinGen, and SimulCAT. Simulations are conducted by involving several variables, namely the ability estimation method (MLE, MAP, and EAP), item parameter estimation method (1PL, 2PL, and 3PL), Efficiency Balanced Information as an item selection method, and stopping rule based on SE which is 0.3. The simulation involves 150 items that characters have been defined in WinGen and the researcher run in SumulCAT 30 replications. Based on the results of the study it can be concluded (1) The most powerful item estimation method is 2PL, (2) the ability to estimate capabilities with EAP and MAP is relatively the same and the MLE indicates the ability interval that can be estimated narrower, (3) efficiency of administered items with EAP and MAP is relatively the same while MLE needs more items.
