İngilizce Kelime Bilgisi Testinin (VST) Bireyselleştirilmiş Bilgisayarlı Test Olarak Uygulanabilirliğinin İncelenmesi
xmlui.mirage2.itemSummaryView.MetaDataShow full item record
Computerized Adaptive Testing (CAT) allows the construct to be measured with fewer items without compromising measurement accuracy. For constructs such as English Vocabulary Size, which requires a large number of items to be measured, CAT is important from this point of view. In this study, in order to measure English vocabulary knowledge in a shorter period of time and with fewer items, the CAT version (CAT-VST) of the Vocabulary Size Test (VST), one of the most widely used tests in the literature to measure English vocabulary knowledge, was developed. The VST is a multiple-choice test consisting of 140 items. First, the validity evidence of the VST was investigated with the data collected from 1622 undergraduate and graduate students with the paper-and-pencil form of the VST. After determining that the VST is a valid assessment tool for measuring English vocabulary size, post-hoc simulations were conducted with the same data. According to the findings obtained from the simulations in which various CAT rules were tested, the most appropriate ability estimation method for real-time BBT application was determined as EAP, item selection method as MFI, termination rule as "SE ≤ .25" and item use frequency control method as "randomesque = 5". After the determination of the most appropriate CAT rules, the CAT-VST was developed with the Concerto platform. Data were collected from sixty undergraduate and graduate students using both the paper-and-pencil and the CAT versions of the VST in order to compare the findings obtained from the two versions. According to the findings, there was a high correlation between the scores obtained from the paper-and-pencil test and the ability scores estimated in the CAT version (R= .83, 95% CI = .73, .90). The average test length was 12 in the CAT version. This result shows that the BBT-VST reliably predicted English vocabulary size using 91% fewer items.