Computerized Adaptive Tests (CAT) are gaining much more attention than ever by the institutions especially the ones attracting students worldwide due to the nature of CAT not allowing the same items to be presented to different individuals taking the test. In this study, it was aimed to investigate of measurement precision and test length in computerized adaptive testing (CAT) under different conditions. The research was implemented as a Monte Carlo simulation study. In line with the purpose of the study, 500 items which response probabilities were modeled with the three parameter logistic (3PL) model were generated. Fixed length (15,20), standard error (SE<.30, SE<.50) termination rules have been used for the study. Additionally, in comparing termination rules, different starting rules (θ=0,-1<θ<1), ability estimation methods (Maksimum Likelihood Estimation (MLE) ,Expected a Posteriori (EAP) and Maximum a Posteriori Probability (MAP)), item selection method (Kullback Leibler Information (KLI) and Maximum Fischer Information (MFI)) have been selected since these are critical in the algorithms of CAT. 25 replications was performed for each condition in the generated data. The results obtained from study were evaluated by using RMSE, bias and fidelity values criterions. R software was used for data generation and analyses. As a result of the study, it was seen that choosing the test starting rule as θ=0 or -1<θ<1 did not cause a significant difference in terms of measurement precision and test length. It was concluded that the termination rule, in which RMSE and bias values were lower than the other conditions, was the 0.30 SE termination rule. When the EAP ability estimation method was used, lower RMSE and bias values were obtained compared to the MLE. It was concluded that the KLI item selection method had lower RMSE and bias values compared to the MFI.

Computerized Adaptive Tests (CAT) are gaining much more attention than ever by the institutions especially the ones attracting students worldwide due to the nature of CAT not allowing the same items to be presented to different individuals taking the test. The aim of this study is to measure the effect of different termination rules on measurement precision and test length in computer adaptive testing. The research was implemented as a Monte Carlo simulation study. The data generation of the computerized adaptive test was carried out using "catR" package. In comparing termination rules, starting rules (b=0 and -1