A Comparative Study between the Nedelsky and Ebel Methods for Determining Cut Scores in a Criterion-Referenced Mathematics Test (An Extracted Research Paper)

Abstract

The purpose of this research was to compare the Nedelsky and Ebel methods for setting a cut score on a criterion-referenced test (CRT) in mathematics for seventh-grade students. The study aimed to determine which method yields a more valid and reliable classification of students' performance into mastery and non-mastery categories. The sample consisted of 440 seventh-grade students selected from various educational settings. To ensure the content validity of the test, a panel of subject matter experts reviewed the test items, and a detailed table of specifications was developed to align each item with specific instructional objectives.

In addition to expert validation, empirical evidence of validity was obtained. The reliability of the test was examined through multiple methods. Internal consistency was assessed using the Kuder–Richardson Formula 20 (KR-20), which yielded a reliability coefficient of 0.73. Furthermore, Livingston’s coefficient was calculated to assess the consistency of classification decisions and was found to be 0.74.

To evaluate and compare the effectiveness of the Nedelsky and Ebel methods in determining cut scores, the researchers applied two decision-based evaluation criteria: the confusion matrix and Berk’s classification index. These methods helped assess the accuracy and stability of mastery classifications based on the derived cut scores.

The findings revealed that the Ebel method outperformed the Nedelsky method in terms of both decision validity and classification reliability. Specifically, the Livingston coefficient for the Ebel method reached 0.98, significantly higher than the 0.74 recorded for the Nedelsky method. The study concluded with practical recommendations and proposed directions for future research focused on enhancing standard-setting practices and test development methodologies.