A Proof of the Duality of the DINA Model and the DINO Model

Variational Bayes Inference for the DINA Model

“…However, it would easily be possible to extend the proposed algorithm to the deterministic input noisy OR gate (DINO) model because the only difference between the DINA and the DINO model is in the definition of the ideal response. Therefore, the VB algorithm for the DINO model can be derived by replacing the ideal response in the proposed method with that of DINO model (see Köhn and Chiu, 2016, to understand the theoretical relationship between the DINA and DINO models).…”

Bayesian DINA Modeling Incorporating Within-Item Characteristic Dependency

“…Despite promising results, some limitations still exist. Although only the DINA model was used in this study, the proposed modeling method can be easily extended to the Deterministic Input Noisy Output “OR” (DINO) model (Templin & Henson, 2006), because the DINA and the DINO models share a “dual” relation (Köhn & Chiu, 2016). However, unlike the DINA and the DINO models that contain 2 I item parameters, different items in more general CDMs (e.g., de la Torre, 2011; Henson et al, 2009; von Davier, 2008) can have different numbers of parameters.…”

Editorial

“…As noted in the Editorial of the last issue of the Journal of Classification, Cognitive Diagnosis Models are becoming increasingly popular, and Chen-Yu Hong, Yu-Wei Chang, and Rung-Ching Tsai continue the trend in this issue by introducing order restrictions to the DINA model (and, from the last issue, we know that the DINA model and the DINO model share a duality, so the results presented should also apply to the DINO model; see Kohn and Chiu, 2016). The current paper solves a problem that I have long been vexed by-namely, the fact that in the traditional DINA model an examinee who had mastered more required attributes could have a lower probability of getting a correct answer than an examinee who had mastered fewer required attributes.…”