predict.parboost

object

Optionally a data frame with new data to
predict

newdata

String determining the type of prediction. The default
<code>"response"</code> is on the scale of the response variable and
<code>"link"</code> is on the scale of the predictors.

type

Additional parameters passed to predict.mboost.


Predict method for <code>parboost</code> objects


Distributed gradient boosting based on the mboost package. The
parboost package is designed to scale up component-wise functional
gradient boosting in a distributed memory environment by splitting the
observations into disjoint subsets, or alternatively using bootstrap
samples (bagging). Each cluster node then fits a boosting model to its
subset of the data. These boosting models are combined in an ensemble,
either with equal weights, or by fitting a (penalized) regression
model on the predictions of the individual models on the complete
data.

predict.parboost: Generate predictions from parboost object

Description

Usage

Arguments

Value

Details

References