estimation methods were compared through simulation with Computerized Adaptive Testing. In this context, estimation errors of item selection and ability parameters were calculated using a simulated dataset based on the three-parameter logistic model, and simulations were conducted via SimulCAT software. In the study, Maximum Likelihood Estimation and Bayesian estimation methods were compared for ability estimation; the accuracy of ability estimation and the average standard errors were calculated for each method using Maximum Fisher Information and Maksimum Likelihood Weighted Information as item selection methods. During the testing process, interim theta values of individuals were also examined, and it was recorded which method yielded better results. A fixed-length rule of 20 items was preferred as the test termination criterion, and the test was terminated for each individual after answering 20 questions. The application was carried out with a total of 1,000 individuals, and item pool consisted of 500 items. The average of the results obtained from 25 replications for each method was used in the analyses. According to results, in the Maximum Likelihood Estimation method, the Maksimum Likelihood Weighted Inform function yielded the most accurate ability estimation with the least error; in the Bayesian method, the Maximum Fisher Information criterion provided the most accurate estimation. In interim ability estimation as well, it can be stated that the Maksimum Likelihood Weighted Inform function in the Maximum Likelihood Estimation method and the Maximum Fisher Information criterion in the Bayesian method yielded better results.