Observed score reliability indices in diagnostic classification models

Quantifying the reliability of latent variable estimates in diagnostic classification models has been a difficult topic, complicated by classification-based nature these models. In this study, we derive observed score indices based on as an extension classical test theory-based reliability. Additionally, conditional sum- and sub-score distributions. manner, various expectations standard error measurement can be calculated for both sub-scores test. The proposed methods provide variety errors attribute estimates, which demonstrate with analysis empirical Moreover, simulation study revealed sub-score-based index was correlated to previously developed mastery index.