Concurrent Validity of the Central Examination of Secondary Education Institutions: Canonical Correlation Analysis

Abstract

The aim of the study is to reveal the concurrent validity of the Central Examination of Secondary Education Institutions (OKMS). For this purpose, the relationship between the OKMS subtest raw scores of the students who took the exam and the 8th grade year-end achievement scores of the courses within the scope of the exam was analyzed by canonical correlation analysis. Grade 8 achievement scores were taken as the independent (predictor) variable and OKMS subtest scores were taken as the dependent (criterion) variable. The study was conducted on 3029 8th grade students who took the OKMS. Only one canonical correlation was found to be significant between the two sets of variables. 8th grade achievement scores were highly positively correlated with OKMS subtest scores. While 8th grade foreign language and science achievement scores had a high predictive power for OKMS subtest raw scores, it was found that the predictive power of the achievement scores of religious culture course in explaining the OKMS subtest raw scores was low. The set of 8th grade scores explained 48.6% of the total variance in the variable set of OKMS subtest raw scores. OKMS subtest variable set explains 60.1% of the total variance in the set of 8th grade scores.