Comparison of Test Equating Methods Based on Item Response Theory According to the Sample Size and Ability Distribution

In this study, it was aimed that equating methods of “mean-mean”, “mean-sigma”, “Heabera” and “Stocking-Lord” were compared in terms of the ability distribution and sample size variables based on Item Response Theory (IRT). Common item nonequivalent groups equating design was used, hi this study 600 dichotomously responded data matrices were generated. Ability parameters of have been estimated from simulated data with expected a posteriori method. Results showed that, in the case of groups having similar and different ability distribution with different sample size (500 and 1000), test equating application with “Stocking-Lord” method gave less equation error has been obtained.