Data Sets for Diagnostic Classification Modeling

Access data sets for demonstrating or testing diagnostic classification models. Simulated data sets can be used to compare estimated model output to true data-generating values. Real data sets can be used to demonstrate real-world applications of diagnostic models.

dcmdata

The goal of dcmdata is to provide easy access to data sets for use with diagnostic classification models.

Installation

You can install the released version of dcmdata from CRAN with:

install.packages("dcmdata")

And the development version from GitHub with:

# install.packages("pak")
pak::pak("r-dcm/dcmdata")

About the data

dcmdata contains both real and simulated data sets for educational and psychological assessment. For more information on each data set, see the linked reference pages.

Real data sets

• ECPE: Assessment data from the Examination for the Certificate of Proficiency in English, as described in Templin and Hoffman (2013).
• Fraction: The fraction subtraction data described by Tatsuoka (2002).
• MCMI: Psychological assessment data from the Millon Clinical Multiaxial Inventory-III, as described in Rossi et al. (2010).
• MDM: A short integer multiplication assessment, as described in MacReady and Dayton (1977).
• PIE: Assessment data from the Pathways for Instructionally Embedded Assessment data, as described by ATLAS (2025).
• ROAR-PA: Data from the Rapid Online Assessment of Reading and Phonological Awareness, as described by Gijbels et al. (2024).
• TIMSS-03: Data from the 2003 grade 8 Trends in International Mathematics and Science Study, as describe by Skaggs et al. (2016).
• TIMSS-07: Data from the 2007 grade 4 Trends in International Mathematics and Science Study, as describe by Park et al. (2011).

Simulated data sets

• DTMR: A data set based on the Diagnostic Teachers’ Multiplicative Reasoning assessment, described in Bradshaw et al. (2014).

Contributions and Code of Conduct

Contributions are welcome. To ensure a smooth process, please review the Contributing Guide. Please note that the dcmdata project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.