Meysam Sadeghi; Mohammad Reza Falsafinezhad; Ali Delavar; Noorali Farrokhi; Ehsan Jamali
Volume 12, Special Issue , June 2018, , Pages 27-43
Abstract
Objective: The purpose of this study was to identify the weight of each of the courses of academic record and scoring based on the psychometric approaches of factor analysis and the continuous IRT model and the approaches based on the viewpoint of the experts of Topsis and AHP, as well as the comparison ...
Read More
Objective: The purpose of this study was to identify the weight of each of the courses of academic record and scoring based on the psychometric approaches of factor analysis and the continuous IRT model and the approaches based on the viewpoint of the experts of Topsis and AHP, as well as the comparison of the effect of the weighting model on variance and the predictive validity of the scores. Methodology: The method of this study was a mixed research method. In order to conduct research in the first part, 11 items (courses) of academic background were taken from the expert group and weighed and prioritized using Topsis and AHP techniques. In the second section, the final third year high school grades of volunteers and admitted students of psychology and counseling at universities across the country were received from the Sanjesh Organization for estimating standard weights in the form of factor analysis and calculating Theta. In the third section, in order to compare different weighing and scoring models, the sample group was firstly scored based on scores derived from all four approaches, and compared in terms of dispersion indexes and predictive validity. Results: The results of the comparison of the four approaches showed that the most variance is related to the IRT continuous modeling method. Also, the results of the data analysis showed that the scores obtained from the continuous IRT model had the highest correlation with the university's average score and the psychology score of the Konkoor. Conclusion: The comparison of the frequency distribution of the score-ability in the framework of all four approaches indicates that the abundance distribution in the IRT encompasses a wider range of abilities and more variance, and also results in higher predictive validity Has enjoyed. Based on this, it seems that with enough information, the test scoring framework can be changed to the theta scores that have a higher predictive validity and higher detection capability.
