predict.conformalIntSplit: Predict Method for conformalIntSplit objects

In lihualei71/cfcausal: Conformal inference of counterfactuals and individual treatment effects

Predict Method for conformalIntSplit objects

Description

Obtains predictive intervals on a testing dataset based on a conformalIntSplit object from conformalInt with useCV = FALSE.

Usage

## S3 method for class 'conformalIntSplit'
predict(
  object,
  Xtest,
  alpha = 0.1,
  wthigh = 20,
  wtlow = 0.05,
  useInf = FALSE,
  ...
)

Arguments

object	an object of class conformalIntSplit; see conformalInt.
Xtest	testing covariates.
alpha	confidence level.
wthigh	upper truncation level of weights; see Details.
wtlow	lower truncation level of weights; see Details.
useInf	if FALSE then replace infinity by the maximum conformity score.
...	other arguments

Details

Given a testing set X_1, X_2, …, X_n and a weight function w(x), the weight of the weighted distribution p_j = w(X_j) / (w(X_1) + \cdots + w(X_n)). In cases where some of p_j are extreme, we truncate p_j at level wthigh and wtlow to ensure stability. If wthigh = Inf, wtlow = 0, no truncation is being used.

Value

predictive intervals. A data.frame with nrow(Xtest) rows and two columns: "lower" for the lower bound and "upper" for the upper bound.

See Also

predict.conformalIntCV, conformalInt.

lihualei71/cfcausal documentation built on Jan. 7, 2023, 1:34 p.m.