Select Parameters for Tree

Usage

tree.control(nobs, mincut=5, minsize=10, mindev=0.01)

Arguments

nobs The number of observations in the training set.
mincut The minimum number of observations to include in either child node. This is a weighted quantity; the observational weights are used to compute the `number'. The default is 5.
minsize The smallest allowed node node: a weighted quantity. The default is 10.
mindev The within-node deviance must be at least this times that of the root node for the node to be split.

Description

The produces default values of mincut and minsize, and ensures that mincut is at least half minsize.

To produce a tree that perfectly fits the data, set mindev=-1 and minsize = 2.

Value

A list
mincut The maximum of the input or default mincut and 1
minsize The maximum of the input or default minsize and 2.
nmax A estimate of the maximum number of nodes that might be grown.
nobs The input nobs.

Author(s)

B.D. Ripley

See Also

tree


[Package Contents]