Predict From A Local Polynomial Lifting Trend Filter

Usage

# S3 method for class 'lpl_tf'
predict(
  object,
  newdata = NULL,
  type = c("response"),
  allow.incomplete = FALSE,
  ...
)

Arguments

object: A "lpl_tf" object.
newdata: Must be NULL; prediction is currently available only at the training points.
type: Prediction type. The current implementation supports only "response".
allow.incomplete: Reserved.
...: Reserved.

Value

Fitted values at the training points.

Examples

if (requireNamespace("genlasso", quietly = TRUE)) {
  X <- matrix(seq(0, 1, length.out = 18), ncol = 1)
  fit <- fit.lpl.tf(X, sin(2 * pi * X[, 1]), degree = 1L,
                    support.type = "knn", support.size = 7L,
                    lambda = 0.1, lambda.selection = "fixed")
  predict(fit)
}
#>  [1]  0.08487544  0.35109733  0.59379848  0.86574578  1.00627490  0.98586848
#>  [7]  0.78858770  0.48655514  0.15890011 -0.15890011 -0.48655514 -0.78858770
#> [13] -0.98586848 -1.00627490 -0.86574578 -0.59379848 -0.35109733 -0.08487544