ClusROC: An R Package for ROC Analysis in Three-Class Classification Problems for Clustered Data

Abstract:

This paper introduces an R package for ROC analysis in three-class classification problems, for clustered data in the presence of covariates, named ClusROC. The clustered data that we address have some hierarchical structure, i.e., dependent data deriving, for example, from longitudinal studies or repeated measurements. This package implements point and interval covariate-specific estimation of the true class fractions at a fixed pair of thresholds, the ROC surface, the volume under the ROC surface, and the optimal pairs of thresholds. We illustrate the usage of the implemented functions through two practical examples from different fields of research.

Cite PDF Tweet

Published

Aug. 26, 2023

Received

May 30, 2022

DOI

10.32614/RJ-2023-035

Volume

Pages

15/1

254 - 270


Footnotes

    References

    Reuse

    Text and figures are licensed under Creative Commons Attribution CC BY 4.0. The figures that have been reused from other sources don't fall under this license and can be recognized by a note in their caption: "Figure from ...".

    Citation

    For attribution, please cite this work as

    To, et al., "ClusROC: An R Package for ROC Analysis in Three-Class Classification Problems for Clustered Data", The R Journal, 2023

    BibTeX citation

    @article{RJ-2023-035,
      author = {To, Duc-Khanh and Adimari, Gianfranco and Chiogna, Monica},
      title = {ClusROC: An R Package for ROC Analysis in Three-Class Classification Problems for Clustered Data},
      journal = {The R Journal},
      year = {2023},
      note = {https://doi.org/10.32614/RJ-2023-035},
      doi = {10.32614/RJ-2023-035},
      volume = {15},
      issue = {1},
      issn = {2073-4859},
      pages = {254-270}
    }