Crandore Hub

cdCAT

Computerized Adaptive Testing with Cognitive Diagnostic Models

A session-based engine for cognitive diagnostic computerized adaptive testing (CD-CAT), the application of adaptive testing to cognitive diagnosis models. Three models are supported: the deterministic inputs, noisy "and" gate (DINA), the deterministic inputs, noisy "or" gate (DINO), and the generalized DINA (GDINA) model. Item selection criteria include Kullback-Leibler (KL) information, posterior-weighted Kullback-Leibler (PWKL), modified posterior-weighted Kullback-Leibler (MPWKL), and Shannon entropy (SHE). Latent attribute profiles are estimated by maximum likelihood estimation (MLE), maximum a posteriori (MAP), or expected a posteriori (EAP). Content balancing, item exposure control, and shadow testing are configurable through constraint functions. The implemented methods follow Cheng (2009) <doi:10.1007/s11336-009-9123-2> and de la Torre (2011) <doi:10.1007/s11336-011-9207-7>. Designed for real-time, item-by-item adaptive applications.

Versions across snapshots

VersionRepositoryFileSize
0.1.0 rolling linux/jammy R-4.5 cdCAT_0.1.0.tar.gz 735.1 KiB
0.1.0 rolling linux/noble R-4.5 cdCAT_0.1.0.tar.gz 735.2 KiB
0.1.0 rolling source/ R- cdCAT_0.1.0.tar.gz 387.0 KiB
0.1.0 latest linux/jammy R-4.5 cdCAT_0.1.0.tar.gz 735.1 KiB
0.1.0 latest linux/noble R-4.5 cdCAT_0.1.0.tar.gz 735.2 KiB
0.1.0 latest source/ R- cdCAT_0.1.0.tar.gz 387.0 KiB
0.1.0 2026-04-23 source/ R- cdCAT_0.1.0.tar.gz 0 B

Dependencies (latest)

Imports

Suggests