DINA Modele Göre Testin Psikometrik Özelliklerinin Belirlenmesi ve Bireysel Dönüt Verilmesi: TIMSS 2015
Yazarlar (3)
Doç. Dr. Mahmut Sami Koyuncu Gazi Üniversitesi, Türkiye
Ayşenur Erdemir
Gazi Üniversitesi, Türkiye
Dr. Öğr. Üyesi Sinem ŞENFERAH Kastamonu Üniversitesi, Türkiye
Makale Türü Açık Erişim Özgün Makale (Ulusal alan endekslerinde (TR Dizin, ULAKBİM) yayınlanan tam makale)
Dergi Adı Türk Eğitim Bilimleri Dergisi
Dergi ISSN 2459-1912
Dergi Tarandığı Indeksler TR DİZİN
Makale Dili Türkçe Basım Tarihi 01-2019
Cilt / Sayı / Sayfa 17 / 1 / 103–120 DOI
Makale Linki https://dergipark.org.tr/tr/pub/tebd/issue/46309/528729
UAK Araştırma Alanları
Eğitimde Ölçme ve Değerlendirme
Özet
The aim of the study is to show how to use DINA model in defining psychometric characteristics of a test and giving students individualized feedback. The data of the study is taken from multiple-choice items in booklet-1 of eighth graders’ mathematics test of TIMSS 2015 Turkey sample. 435 students took booklet-1. The parameters of DINA model were estimated via R Studio and interpreted by comparing with CTT and IRT parameters. Additionally, diagnostic profile report example for individualized feedback was constructed. The result of the study shows that DINA model has a good fit (SRMSR, MADcor, MADQ3, MADaQ3, and RMSEA < 0.05). The parameters of DINA model are similar to those of CTT and IRT. The reliability values of DINA, CTT and IRT are (Pc)=0.913, KR-20=0.80 and marginal reliability=0.70, respectively. Thus, reliability of DINA model is bigger than the others’ values. As a result, it is suggested that DINA model can be used to report psychometric characteristics of a test. In addition, it can be used to give detailed individualized feedback to students, which is different from CTT and IRT.
Anahtar Kelimeler
BM Sürdürülebilir Kalkınma Amaçları
Atıf Sayıları

Paylaş