FDboost (version 0.3-2)

mstop.validateFDboost: Methods for objects of class validateFDboost

Description

Methods for objects that are fitted to determine the optimal mstop and the prediction error of a model fitted by FDboost.

Usage

# S3 method for validateFDboost
mstop(object, riskopt = c("mean", "median"), ...)

# S3 method for validateFDboost print(x, ...)

# S3 method for validateFDboost plot(x, riskopt = c("mean", "median"), ylab = attr(x, "risk"), xlab = "Number of boosting iterations", ylim = range(x$oobrisk), which = 1, modObject = NULL, predictNA = FALSE, names.arg = NULL, ask = TRUE, ...)

plotPredCoef(x, which = NULL, pers = TRUE, commonRange = TRUE, showNumbers = FALSE, showQuantiles = TRUE, ask = TRUE, terms = TRUE, probs = c(0.25, 0.5, 0.75), ylim = NULL, ...)

Arguments

object

object of class validateFDboost

riskopt

how the risk is minimized to obtain the optimal stopping iteration; defaults to the mean, can be changed to the median.

...

additional arguments passed to callies.

x

an object of class validateFDboost.

ylab

label for y-axis

xlab

label for x-axis

ylim

values for limits of y-axis

which

In the case of plotPredCoef() the subset of base-learners to take into account for plotting. In the case of plot.validateFDboost() the diagnostic plots that are given (1: empirical risk per fold as a funciton of the boosting iterations, 2: empirical risk per fold, 3: MRD per fold, 4: observed and predicted values, 5: residuals; 2-5 for the model with the optimal number of boosting iterations).

modObject

if the original model object of class FDboost is given predicted values of the whole model can be compared to the predictions of the cross-validated models

predictNA

should missing values in the response be predicted? Defaults to FALSE.

names.arg

names of the observed curves

ask

defaults to TRUE, ask for next plot using par(ask = ask) ?

pers

plot coefficient surfaces as persp-plots? Defaults to TRUE.

commonRange,

plot predicted coefficients on a common range, defaults to TRUE.

showNumbers

show number of curve in plot of predicted coefficients, defaults to FALSE

showQuantiles

plot the 0.05 and the 0.95 Quantile of coefficients in 1-dim effects.

terms

logical, defaults to TRUE; plot the added terms (default) or the coefficients?

probs

vector of quantiles to be used in the plotting of 2-dimensional coefficients surfaces, defaults to probs = c(0.25, 0.5, 0.75)

Details

The function mstop.validateFDboost extracts the optimal mstop by minimizing the mean (or the median) risk. plot.validateFDboost plots cross-validated risk, RMSE, MRD, measured and predicted values and residuals as determined by validateFDboost. The function plotPredCoef plots the coefficients that were estimated in the folds - only possible if the argument getCoefCV is TRUE in the call to validateFDboost.