A Study of the Quality of Scholastic Aptitude Test by Applying Modern Test Theories
Main Article Content
Abstract
The objective of this research was to study the quality of the scholastic aptitude test by applying modern test theories through Item Response Theory, test parameters, reliability, and differential item functioning. The secondary data were collected from the SWUSAT Test Development Project 2014, which consists of a test for all 4 subjects: Verbal Factor, Number Factor, Reasoning Factor and Spatial Factor. The data analysis was divided into 3 steps as follows: Step 1: Data preparation according to the studied factors, the researcher performed the analysis of the basic statistics of the data by analyzing the preliminary data with descriptive statistics, i.e. frequency, percentage. Step 2: Analyze test parameters using a 2-parameter test response model based on parameters, discriminant power (a), difficulty (b) parameter, and reliability. Step 3: Analysis of data with differential item functioning.
The results of the research were as follows:
The results of the analysis of the individual parameters of the 4-subject aptitude test with the 2-parameter test response analysis model were determined from the discriminant power parameter (a) and the difficulty parameter. (b) When considering the results of the course analysis, it was found that all subjects had a predominantly number of tests with a parameter that met the quality criteria, including a relatively high reliability level.
The results of analysis of the differential item functioning and the SWUSAT test, which measures Verbal Factor, Number Factor, Reasoning Factor and Spatial Factor. The difference of the test was in the range of 6.67% - 43.33, with two tests having a number of questions that performed differently, with males being more likely to get the correct answers than females, while the other two had the same number of questions. And all tests performed at a low level of different functions
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.