Multidimensional cross-validated estimation of the empirical risk for hyper-parameter selection,
for an object of class FDboostLSS
setting the folds per default to resampling curves.
# S3 method for FDboostLSS
cvrisk(object, folds = cvLong(id = object[[1]]$id,
weights = model.weights(object[[1]])), grid = NULL, papply = mclapply,
trace = TRUE, fun = NULL, ...)
an object of class FDboostLSS
.
a weight matrix a weight matrix with number of rows equal to the number of observations. The number of columns corresponds to the number of cross-validation runs, defaults to 25 bootstrap samples, resampling whole curves
defaults to a grid up to the current number of boosting iterations.
The default generates the grid according to the defaults of
cvrisk.mboostLSS
and cvrisk.nc_mboostLSS
for
models with cyclic or noncyclic fitting.
(parallel) apply function, defaults to mclapply
,
see cvrisk.mboostLSS
for details
print status information during cross-validation? Defaults to TRUE
.
if fun
is NULL
, the out-of-sample risk is returned.
fun
, as a function of object
,
may extract any other characteristic of the cross-validated models. These are returned as is.
additional arguments passed to mclapply
.
An object of class cvriskLSS
(when fun
was not specified),
basically a matrix containing estimates of the empirical risk for a varying number
of bootstrap iterations. plot
and print
methods are available as well as an
mstop
method, see cvrisk.mboostLSS
.
The function cvrisk.FDboostLSS
is a wrapper for
cvrisk.mboostLSS
in package gamboostLSS.
It overrieds the default for the folds, so that the folds are sampled on the level of curves
(not on the level of single observations, which does not make sense for functional response).
cvrisk.mboostLSS
in packge gamboostLSS.