“…For instance, Akbay ( 2016 ) showed that the non-parametric cognitive diagnosis approach (Chiu and Douglas, 2013 ) performs as well as the CDM based empirical Bayes estimation method for attribute classification in the presence of small sample sizes such as 250, 500, and 1,000. Sünbül and Kan ( 2016 ) investigated the effect of several factors including number of attributes and sample size (i.e., 200, 500, 1,000, and 5,000) on model fit, item recovery, and classification accuracy of the DINA model. The number of attributes and sample size had positive effects on the model estimates.…”