relaxo (version 0.1-2)

predict.relaxo: predict method for class relaxo

Description

Prediction with Relaxed Lasso

Usage

"predict"(object, newX = NULL, lambda = NULL, phi = NULL,...)

Arguments

object
An object of class relaxo
newX
A data frame or matrix containing new data. If not given, the prediction for the original training data is returned.
lambda
The penalty parameter for variable selection.
phi
The relaxation parameter in the interval [0,1].
...
other arguments (currently ignored).

Value

A numerical vector, containing the predictions for the new data points (or the fitted values if newX=NULL).

References

N. Meinshausen, "Relaxed Lasso", Computational Statistics and Data Analysis, to appear. http://www.stat.berkeley.edu/~nicolai