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.
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 ...".
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}
}