sid_p: Calculate the p-values for a list of trees.

Description Usage Arguments Value

Description

Calculate the p-value for a list of trees (groupings).

Usage

1
2
3
sid_p(data_train, data_test, tree_list, g0 = NULL, classifier = svm,
  Rmin = 250, Rmax = 500, alpha = 0.05, z = 2.57, parallel = TRUE,
  early_stopping = FALSE)

Arguments

data_train

Training data.

data_test

Testing data.

tree_list

List of trees.

g0

The Baseline goodness, if known. Can be NULL (default).

classifier

A classifier function, default is svm (from the e1071 package).

Rmin

Ninimum number of replications. Default is 250.

Rmax

Maximum number of replications. Default is 500.

alpha

The confidence level at which we are evaluating statistical significance of the tree.

z

Parameter for confidence band. Use 1.96 for 95 percent, 2.25 for 97.5 percent and 2.57 for 99 percent. Default is 2.57.

parallel

Calculate in parallel (Boolean, default is TRUE).

early_stopping

Use early stopping. Default is FALSE in which case Rmin samples are used to calculate p-values. If TRUE at least Rmin and at most Rmax values are used. '

Value

The treelist with the p-values added.


bwrc/astrid-r documentation built on May 13, 2019, 9:08 a.m.