Investigation of the effect of guessing on test equating with different equating methods

The aim of the study is to investigate whether guessing is a factor or not to equate English tests by using linear and equipercentile equating with single group design. In addition, it was aimed to equate the scores of English Asssesment tests by using these traditional methods and determine which of those is proper. The data were gathered from 1681 8th grade students in various public schools in Turkey. For the data analysis process, at first descriptive statistical analysis (mean, difficulty, variance, skewness, kurtosis and reliability) was utilized to check the assumptions of equation of the tests scores. For the second phase, the equated points for scores with guessing and without guessing were given by using the methods of linear and equipercentile-equating. At the final phase, the weighted mean square error (WMSE), the root mean squared difference (RMSD) and the mean signed difference (MSD) were calculated to identify the more suitable method for equating scores. Based on the results, equipercentile-equating method yielded less weighted mean square error, root mean squared difference and mean signed difference than linear equating method when English tests were equated. At last, after elimination of the guessing factor from scores, linear equating method showed less weighted mean square error root mean squared difference and mean signed difference than the equipercentile-equating.