Çok Kategorili Bireyselleştirilmiş Bilgisayarlı Test Uygulamalarının Farklı Madde Seçim Yöntemlerinde Sonlandırma Kuralları Açısından İncelenmesi

Abstract

In this study, it is aimed to compare the different item selection methods and stopping rules used in Computerized Adaptive Testing (CAT) applications with simulative data by using the item parameters of Vocational Maturity Scale and to test the validity of CAT application by using the most appropriate item selection method and stopping rule. For this purpose, simulative data produced by using Vocational Maturity Scale item parameters were analyzed under different item selection methods and stopping rules by calculating the average number of items, standard error averages, correlation coefficients, bias and RMSE statistics. Under different item selection methods, standard error averages, correlation coefficients, bias and RMSE statistics showed similar results for all conditions. Although there is no difference between item selection methods in terms of these statistics, considering the average number of items, the appropriate method to be used in CAT application was determined item selection method as Maximum Fisher Information (MFI) and stopping rule as SE<0.30. After the simulation study, in the second phase of the study, CAT application of the Vocational Maturity Scale is prepared using CONCERTO platform. The paper-pencil test application of the Vocational Maturity scale and CAT application were applied to 33 students. As a result of CAT application estimation has been made by applying minimum 8 items and maximum 28 items for 33 individuals. A moderate, positive and statistically significant relationship between CAT application and vocational maturity levels obtained from paper-pencil test were found (r=0.535, p<0.05).