Structural models for diagnostic classification

Structural models define how the attributes are related to one another. The currently supported options for structural models are: unconstrained and independent attributes. See details for additional information on each model.

Usage

unconstrained()

independent()

Value

A structural model object.

Details

The unconstrained structural model places no constraints on how the attributes relate to each other. This is equivalent to a saturated model described by Hu & Templin (2020) and in Chapter 8 of Rupp et al. (2010).

The independent attributes model assumes that the presence of the attributes are unrelated to each other. That is, there is no relationship between the presence of one attribute and the presence of any other. For an example of independent attributes model, see Lee (2016).

References

Hu, B., & Templin, J. (2020). Using diagnostic classification models to validate attribute hierarchies and evaluate model fit in Bayesian Networks. Multivariate Behavioral Research, 55(2), 300-311. doi:10.1080/00273171.2019.1632165

Lee, S. Y. (2016). Cognitive diagnosis model: DINA model with independent attributes. https://mc-stan.org/documentation/case-studies/dina_independent.html

Rupp, A. A., Templin, J., & Henson, R. A. (2010). Diagnostic measurement: Theory, methods, and applications. Guilford Press.

Examples

unconstrained()
#> <dcmstan::UNCONSTRAINED>
#>  @ model     : chr "unconstrained"
#>  @ model_args: list()

independent()
#> <dcmstan::INDEPENDENT>
#>  @ model     : chr "independent"
#>  @ model_args: list()