cdmTools - Useful Tools for Cognitive Diagnosis Modeling

Provides useful tools for cognitive diagnosis modeling (CDM). The package includes functions for estimating CDMs such as the restricted DINA or DINO (R-DINA or R-DINO) models (Nájera et al., 2023; <doi:10.3102/10769986231158829>), the G-DINA model for forced-choice blocks (Nájera et al., 2024; <doi:10.1111/bmsp.12393>), and the general nonparametric classification method (Chiu et al., 2018; <doi:10.1007/s11336-017-9595-4>). Additionally, methods for identifying the latent structure of CDMs are also available, such as dimensionality assessment via parallel analysis and automated fit comparison (Nájera et al., 2021; <doi:10.3389/fpsyg.2021.614470>), as well as empirical Q-matrix validation and estimation using the Hull method (Nájera et al., 2021; <doi:10.1111/bmsp.12228>) and the discrete factor loading method (Wang et al., 2018; <doi:10.1007/978-3-319-77249-3_29>). Other practical functions for CDM applications include corrected classification accuracy estimation via multiple imputation (Kreitchmann et al., 2022; <doi:10.3758/s13428-022-01967-5>), model-based recursive partitioning to detect non-invariant subpopulations (Nájera et al., in press), person-fit evaluation (Santos et al., 2020; <doi:10.1007/s00357-019-09325-5>), and model identifiability assessment (Gu and Xu, 2021; <doi:10.5705/ss.202018.0410>). Lastly, the package also provides useful functions for CDM simulation studies, such as random Q-matrix generation and forced-choice data generation.