The Effects of Sample Size and Test Length on the Accuracy of Equating Polynomial Scores using Kernel Method

Abstract

This study explored the effects of sample size, test length on final equating results of Kernel Method when using the nonequivalent groups anchor test )NEAT( design. The equating method was evaluated using an equating criterion )SEE, RMSE(. Standard error of equating differences between the criterion scores and equated scores, and root mean square error of the differences )RMSE( were used as measures to compare the method to the criterion equating. The results indicated that the large sample size reduces the standard error of the equating and also residuals. The results indicated that test length affects the standard error as the tall test gives large values for the standard error, and the standard residuals.