estimateErrorParams: Estimate prediction error distribution parameters
In forestError: A Unified Framework for Random Forest Prediction Error Estimation

Estimates the prediction error distribution parameters requested in the input to quantForestError.

estimateErrorParams(
  train_nodes,
  test_nodes,
  mspewhat,
  biaswhat,
  intervalwhat,
  pwhat,
  qwhat,
  mcrwhat,
  alpha,
  n.test
)

`train_nodes`	A `data.table` indicating which out-of-bag prediction errors are in each terminal node of each tree in the random forest. It must be formatted like the output of the `findOOBErrors` function.
`test_nodes`	A `data.table` indicating which test observations are in each terminal node of each tree in the random forest. It must be formatted like the output of the `findTestPreds` function.
`mspewhat`	A boolean indicating whether to estimate conditional MSPE.
`biaswhat`	A boolean indicating whether to estimate conditional bias.
`intervalwhat`	A boolean indicating whether to estimate conditional prediction intervals.
`pwhat`	A boolean indicating whether to estimate the conditional prediction error CDFs.
`qwhat`	A boolean indicating whether to estimate the conditional prediction error quantile functions.
`mcrwhat`	A boolean indicating whether to estimate the conditional misclassification rate.
`alpha`	A vector of type-I error rates desired for the conditional prediction intervals; required if `intervalwhat` is `TRUE`.
`n.test`	The number of test observations.

This function is for internal use.

A data.frame with one or more of the following columns:

`pred`	The random forest predictions of the test observations
`mspe`	The estimated conditional mean squared prediction errors of the random forest predictions
`bias`	The estimated conditional biases of the random forest predictions
`lower_alpha`	The estimated lower bounds of the conditional alpha-level prediction intervals for the test observations
`upper_alpha`	The estimated upper bounds of the conditional alpha-level prediction intervals for the test observations
`mcr`	The estimated conditional misclassification rate of the random forest predictions

In addition, one or both of the following functions:

`perror`	The estimated cumulative distribution functions of the conditional error distributions associated with the test predictions
`qerror`	The estimated quantile functions of the conditional error distributions associated with the test predictions

Benjamin Lu <b.lu@berkeley.edu>; Johanna Hardin <jo.hardin@pomona.edu>

forestError documentation built on Aug. 11, 2021, 1:06 a.m.