Higher-order latent trait models for cognitive diagnosis

By Jimmy de la Torre, J. Douglas. 2004

603 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/aec78d56473f8a5c68186f237e751bed1d7793d0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

Robustness of Hierarchical Modeling of Skill Association in Cognitive Diagnosis Models (2008, methodology): “In the context of the DINA and NIDA models, a higher order unidimensional latent trait has been modeled by de la Torre and Douglas (2004). In their article, the higher order latent trait models of the attribute space were fit with the DINA (both single and multiple strategies) and NIDA models.”
Simultaneous Estimation of Overall and Domain Abilities: A Higher-Order IRT Model Approach (2009, background): “Contemporaneously, a hierarchical structure of ability organization has been well accepted in psychological research and practices (e.g., Carrol, 1993; Cronbach & Snow, 1977).”
On the Analysis of Fraction Subtraction Data: The DINA Model, Classification, Latent Class Sizes, and the Q-Matrix (2011, methodology): “The DINA model has been fit within a fully Bayesian framework using Markov chain Monte Carlo (MCMC) methods (e.g., de la Torre & Douglas, 2004, 2008; Henson et al., 2009; Junker & Sijtsma, 2001).”
What CDM Can Tell About What Students Have Learned: An Analysis of TIMSS Eighth Grade Mathematics (2015, methodology): “In addition, CDMs, including the DINA model, are also related to multidimensional IRT models that measures multiple traits (Junker & Sijtsma, 2001); however, the fundamental difference between the DINA model and multidimensional IRT models is in classifying individuals as masters.”
A Note on Comparing Examinee Classification Methods for Cognitive Diagnosis Models (2011, methodology): “(We note that running 25 replications of a simulation experiment has been deemed adequate for investigating examinee classification accuracy and item parameter estimation in previous studies; de la Torre & Douglas, 2004, 2008.)”
Unique Characteristics of Diagnostic Classification Models: A Comprehensive Review of the Current State-of-the-Art (2008, methodology): “In addition to simply including multiple latent variables at the same levels, DCM for hierarchies of latent variables have also been proposed (de la Torre & Douglas, 2004; von Davier, 2007) similar to hierarchical FA models (McDonald, 1999) and hierarchical IRT models (Sheng & Wikle, 2008).”
On the Estimation of Standard Errors in Cognitive Diagnosis Models (2018, background): “Different models can be assumed to reduce the number of parameters (de la Torre & Douglas, 2004; Rupp et al., 2010).”
Skills Diagnosis Using IRT-Based Latent Class Models (2007, methodology): “Haertel (1984, 1990) and by Gitomer and Yamamoto (1991), whereas an MCMC algorithm has been developed by de la Torre and Douglas (2004), who also developed MCMC algorithms for NIDA and for the compensatory MCLCM.”
The Effects of Q-Matrix Misspecification on Parameter Estimates and Classification Accuracy in the DINA Model (2008, methodology): “The DINA model (e.g., de la Torre & Douglas, 2004; Junker, 1999; Junker & Sijtsma, 2001; see Macready & Dayton, 1977) is, like most multiple classification models, a noncompensatory model that uses a conjunctive condensation function (Maris, 1995, 1999).”
Estimating Classification Consistency and Accuracy for Cognitive Diagnostic Assessment. (2012, methodology): “…often referred to as cognitive diagnostic models or diagnostic classification models in the measurement literature, have been devised (e.g., de la Torre & Douglas, 2004; Embretson, 1984; Gierl, Cui, & Hunka, 2008; Hartz, 2002; Junker & Sijtsma, 2001; Mislevy, Steinberg, & Almond, 2003;…”
Statistical Refinement of the Q-Matrix in Cognitive Diagnosis (2013, methodology): “Therefore, the model parameter estimates from their study (see Tables 11 and 12 on pp. 350-351, de la Torre and Douglas, 2004) were used to generate 25 data sets, each with 536 examinees and 20 items requiring possession of up to eighty skills for a correct response.”