The Answer is in the Question: A Guide for Describing and Investigating the Conceptual Foundations and Statistical Properties of Cognitive Psychometric Models

Abstract

One of the most revolutionary advances in psychometric research during the last decades has been the systematic development of statistical models that allow for cognitive psychometric research (CPR) to be conducted. Many of the models currently available for such purposes are extensions of basic latent variable models in item response theory (IRT). While the requirements of basic IRT models in terms of data collection designs, measurement scales of variables, and sample sizes for learners and items are relatively well understood, the added requirements that the cognitive components of modeling processes for CPR bring along with them are understood to a much lesser degree. Therefore, this article contains a guide in the form of a series of questions, which support measurement and substantive specialists in describing and investigating the conceptual foundations and statistical properties of models for CPR. An application of the guide to the rule-space methodology (e.g., Tatsuoka, 1983Tatsuoka, , 1985Tatsuoka, , 1995 is presented, which extends the conceptual-logical discussion of Gierl, Leighton, and Hunka (2000) by focusing more heavily on cognitive and statistical considerations.

Obtaining Diagnostic Classification Model Estimates Using Mplus

“…In recent years, new psychometric methods have been developed that can provide precise and detailed information about the latent attributes or skills examinees may possess as indicated by their item responses. Although diagnostic classification models (DCMs; Rupp & Templin, ) have been the focus of numerous articles, books, and conference presentations (also known cognitive diagnosis models, e.g., Leighton & Gierl, ; Rupp, ), most of this work has been heavily technical and limited to the statistical portion of the psychometric community. We argue this is largely due to the lack of available software for researchers and practitioners who wish to use diagnostic classification models in their testing programs and empirical research.…”

Dina Model İle Geli̇şti̇ri̇len Bi̇r Testi̇n Psi̇kometri̇k Özelli̇kleri̇ni̇n Beli̇rlenmesi̇

“…BTM olarak ifade edilen modeller literatürde; sınırlandırılmış örtük sınıf modelleri (restricted latent class models) (Haertel, 1989), bilişsel psikometrik modeller (cognitive psychometric models) (Rupp, 2007), çoklu sınıflandırma modelleri (multiple classification models) ve yapısal madde tepki kuramı modelleri (structured item response theory models) (Rupp ve Mislevy, 2007) gibi farklı isimler almıştır. Modellere verilen farklı isimlerin bilişsel tanı modeli adı altında yaygınlaşmasında modellerin bireylere ilişkin tanısal profil oluşturmayı hedeflemesi etkili olmuştur.…”

An Illustration of Diagnostic Classification Modeling in Student Learning Outcomes Assessment

“…Therefore, another key component in DCMs is that the attributes thought to influence item responses are specified prior to the analysis and justified through theoretical grounds (Rupp, 2007). SDA6 items were written by Cluster 5 faculty, experts in the field of psychosocial research, with the purpose of measuring a specific psychosocial research learning outcome.…”