send.down.VI.ITR: Sends testing data and permuted testing data down a bootstrap...

In kdoub5ha/mvITR: Discovery of risk controlled individualized treatment rules (ITRs)

Description

Sends dat.new down a tree inside a random forest. Calcuates value and permuted value for variable importance measures

Usage

send.down.VI.ITR(dat.new, tre, col.y, col.r, col.trt, col.prtx, risk.threshold,
  lambda, ctg = NULL, n0 = n0, N0 = N0, revise.tree = T, depth = 1,
  AIPWE = AIPWE)

Arguments

dat.new	the new data set being sent down the tree. Required input.
tre	constructed tree.
col.y	the response variable. Required input.
col.trt	the treatment indicator. Must be binary. Required input.
col.prtx	the probability of being assigned to treatment group. Required input.
ctg	identifies the categorical input columns. Defaults to NA. Not available yet.
n0	minimum number of treatment/control observations needed in a split to call a node terminal. Defaults to 5.
N0	minimum number of observations needed in a node to stop splitting.
revise.tree	internal variable.
depth	internval variable
AIPWE	indicator for AIPWE estimation.

Value

tre0	input tree with score from original tree and score from permutation from each variable used in the tree
score	score from the permuted data

kdoub5ha/mvITR documentation built on April 7, 2020, 3:59 a.m.