THE IMPACT OF CHANCE SUCCESS ON TEST EQUATING

The objective of this study is to find out whether chance scores effects test equating, or not. Single group design, and linear equating and equipercentile equating were used in the study. The data analysis was performed at three stages. At the first stage, it was checked whether equating conditions are fulfilled for test score with and without the chance success. It was identified that there is no significant difference at 0.05 level between the two situations with respect to the mean difficulties, reliabilities, means and variances. Furthermore, at the end of the factor analysis performed, it can be said that both tests measure the same construct. At the second stage, the equated points were found by using linear and equipercentile equating. At the third stage, weighted mean square error of these methods was found, and the method with the lowest weighted mean square error was accepted as the most suitable equating method. At the end of the study, it was found out that; while linear equating is the most suitable method for equating of test points with chance success; equipercentile equating is the most suitable method for equating test points without chance success. Overall, it was observed in the study that the equating error is the lowest for equipercentile equating without chance success.