BlackBoostModel: Gradient Boosting with Regression Trees

Description

Gradient boosting for optimizing arbitrary loss functions where regression trees are utilized as base-learners.

Usage

BlackBoostModel(
  family = NULL,
  mstop = 100,
  nu = 0.1,
  risk = c("inbag", "oobag", "none"),
  stopintern = FALSE,
  trace = FALSE,
  teststat = c("quadratic", "maximum"),
  testtype = c("Teststatistic", "Univariate", "Bonferroni", "MonteCarlo"),
  mincriterion = 0,
  minsplit = 10,
  minbucket = 4,
  maxdepth = 2,
  saveinfo = FALSE,
  ...
)

Value

MLModel class object.

Arguments

family: optional Family object. Set automatically according to the class type of the response variable.
mstop: number of initial boosting iterations.
nu: step size or shrinkage parameter between 0 and 1.
risk: method to use in computing the empirical risk for each boosting iteration.
stopintern: logical inidicating whether the boosting algorithm stops internally when the out-of-bag risk increases at a subsequent iteration.
trace: logical indicating whether status information is printed during the fitting process.
teststat: type of the test statistic to be applied for variable selection.
testtype: how to compute the distribution of the test statistic.
mincriterion: value of the test statistic or 1 - p-value that must be exceeded in order to implement a split.
minsplit: minimum sum of weights in a node in order to be considered for splitting.
minbucket: minimum sum of weights in a terminal node.
maxdepth: maximum depth of the tree.
saveinfo: logical indicating whether to store information about variable selection in info slot of each partynode.
...: additional arguments to ctree_control.

Details

Response types:: binary factor, BinomialVariate, NegBinomialVariate, numeric, PoissonVariate, Surv
Automatic tuning of grid parameters:: mstop, maxdepth

Default values and further model details can be found in the source links below.

Examples

Run this code

# \donttest{
## Requires prior installation of suggested packages mboost and partykit to run

data(Pima.tr, package = "MASS")

fit(type ~ ., data = Pima.tr, model = BlackBoostModel)
# }