Testlerin Boyutluluğunun, Ortak Madde Formatının, Yetenek Dağılımının Vve Ölçek Dönüştürme Yöntemlerinin Karma Testlerin Eşitlenmesine Etkisi

Abstract

The purpose of this study was to examine the impact of test dimensionality (unidimensional versus multidimensional), characteristics of common-item set (format representative versus non-representative), differences in group ability distributions (equivalent versus nonequivalent), and different scale transformation methods on preserving equity property with mixed-format test equating. The study was conducted by using item response theory (IRT) true score equating (TSE) and IRT observed score equating (OSE) methods under non-equivalent groups anchor test design. The equity property was evaluated based on first-order equity (FOE) and second-order equity (SOE) by calculating D1 and D2 indexes. The results showed that in terms of FOE property criteria, all investigated factors had significant effect on TSE and OSE results. Similarly, based on SOE property except for common-item characteristics all factors had significant effect on both TSE and OSE results.