Given a desired family-wise error rate (FWER) and a stability path calculated with stability.path
the function selects an stable set of features and plots the stability path and the corresponding regularization path.
1 2 3 |
x |
an object of class "stabpath" as returned by the function |
error |
the desired type I error level w.r.t. to the chosen type I error rate. |
type |
The type I error rate used for controlling the number falsely selected variables. If |
pi_thr |
the threshold used for the stability selection, should be in the range of 0.5 > pi_thr < 1. |
xvar |
the variable used for the xaxis, e.g. for "lambda" the selection probabilities are plotted along the log of the penalization parameters, for "norm" along the L1-norm and for "dev" along the fraction of explained deviance. |
col.all |
the color used for the variables that are not in the estimated stable set |
col.sel |
the color used for the variables in the estimated stable set |
... |
further arguments that are passed to matplot |
a list of four objects
stable |
a vector giving the positions of the estimated stable variables |
lambda |
the penalization parameter used for the stability selection |
lpos |
the position of the penalization parameter in the regularization path |
error |
the desired type I error level w.r.t. to the chosen type I error rate |
type |
the type I error rate |
Martin Sill \ m.sill@dkfz.de
Meinshausen N. and Buehlmann P. (2010), Stability Selection, Journal of the Royal Statistical Society: Series B (Statistical Methodology) Volume 72, Issue 4, pages 417-473.
Sill M., Hielscher T., Becker N. and Zucknick M. (2014), c060: Extended Inference with Lasso and Elastic-Net Regularized Cox and Generalized Linear Models, Journal of Statistical Software, Volume 62(5), pages 1–22.
http://www.jstatsoft.org/v62/i05/
stabsel,stabpath
1 2 3 4 5 6 7 8 9 |
Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.
All documentation is copyright its authors; we didn't write any of that.