pROC: an open-source package for R and S+ to analyze and compare ROC curves.
Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez JC, Müller M. · 2011
Read pROC: an open-source package for R and S+ to analyze and compare ROC curves. by Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez JC, Müller M. (2011) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc3068975.txt.
Description
Robin and coauthors released in 2011 a software package for drawing and rigorously comparing ROC curves, the standard graphs for judging diagnostic tests and classifiers. A curve plots how a test trades catching true cases against false alarms as its cutoff moves. Papers often compare curves loosely, without proper statistics, and small gaps get overread.
Their package, pROC, builds the curves and adds confidence ranges, smoothing options, and formal tests for whole or partial curve areas. It runs in two popular statistics environments, one free and one commercial, with a friendly interface in the latter. A worked case on published clinical data shows a typical analysis end to end. The authors stress that comparing tests at the cutoff ranges doctors actually use matters most. The tool is free under an open license.
Catalog record
| CREATOR | Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez JC, Müller M. |
|---|---|
| YEAR | 2011 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |