| Resumo: | The Receiver Operating Characteristic (ROC) curve analysis and the resulting plot can be used as a tool to select optimal models of possibility and to discard those of inferior quality from the cost of context (or class distribution). Presently, this type of analysis is used in a variety of fields from the medical community, bioinformatics, military and finance. There is a variety of software packages available for ROC analysis, and this analysis will focus on those specific of R and open source. The chosen packages were: ROCR, Verification, caTools, Comp2ROC, and Epi available on CRAN, and the ROC library from Bioconductor. This work intends to make a comparative analysis of the main characteristics of these R packages.
|
|---|