Open AccessExamining the Two Categorical Datas by Jmetrik, Bilog-Mg and Irtpro with Application of Mathematics Exam
Author(s) -
Gökhan Aksu,
Çiğdem Reyhanlioğlu,
Mehmet Taha Eser
Publication year - 2017
Publication title -
european scientific journal
Language(s) - English
Resource type - Journals
eISSN - 1857-7881
pISSN - 1857-7431
DOI - 10.19044/esj.2017.v13n33p20
Subject(s) - categorical variable , item response theory , statistics , logistic regression , mathematics education , set (abstract data type) , descriptive statistics , test (biology) , mathematics , data set , psychology , computer science , psychometrics , paleontology , biology , programming language
The aim of this study was to examination of two-category rated mathematics course final exam based on Item Response Theory data analyzed with the help of 2-Parameter Logistic Model and determination of the ability and standard errors with the help of different programs. This study involves a comparative interpretation of some descriptive statistics and analysis. Therefore, research has characterized as relational model which is one of the general survey models. For this purpose, 771 students’ final achievement test responses to a 20-point final exam, were analyzed by BILOG, IRT PRO and JMETRİK programs. Item Response Theory assumptions were analyzed with SPSS and Factor 9.3 programs. Working as a result of the analysis of data all of the IRT assumptions are met and the most appropriate model of data set has been concluded that the twoparameter logistic model. The study also found that there is a statistically significant relationship between the estimated parameters related to individual ability and error at the level of .01. Especially compared to the others there is also significant relationship between JMETRİK and IRT PRO. Different models and methods of research proposals have been made in terms of response patterns to be analyzed a gain for the same data set.