Description Details Author(s) References See Also
This package can be used for proposing prognostic scoring systems based on few explanatories variables or based on thousand features from microarray. The methodology is adapted to complete data (penalized logistic regression associated with ROC curve) incomplete time-to-event data (penalized Cox model associated with ROC time-dependent ROC curve).
Package: | ROC632 |
Type: | Package |
Version: | 0.6 |
Date: | 2013-27-12 |
License: | GPL (>=2) |
LazyLoad: | yes |
ROC | This function allows to compute traditional ROC curves (complete data) for |
\mbox{ } | a binary outcome and a continuous marker. |
AUC | This function computes the area under ROC curve using the trapezoidal rule |
\mbox{ } | based on two vectors of sensitivities and specificities. |
boot.ROC | This function allows the construction of a prognostic or |
\mbox{ } | a diagnostic signature (complete data) by using bootstrap-based algorithms |
\mbox{ } | for correcting the overfitting. |
boot.ROCt | This function allows the construction of a prognostic |
\mbox{ } | signature (time-to-event data) by using bootstrap-based algorithms |
\mbox{ } | for correcting the overfitting. |
Y. Foucher <Yohann.Foucher@univ-nantes.fr>
R. Danger and Y. Foucher. Time dependent ROC curves for the estimation of true prognostic capacity of microarray data. Statistical Applications in Genetics and Molecular Biology. 2012 Nov 22;11(6):Article 1.
URL: http://www.divat.fr
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.