Backfitting for Additive Models — backfitter • ICEbox

Fits a model of the form \(\hat{f}(x) = \hat{g}_{1}(x_S) + \hat{g}_{2}(x_C)\) using backfitting.

Usage

backfitter(
  X,
  y,
  predictor,
  fitMethod,
  predictfcn,
  eps = 0.01,
  iter.max = 10,
  verbose = TRUE,
  ...
)

X: The design matrix.
y: The response vector.
predictor: The name or index of the predictor of interest (\(x_S\)).
fitMethod: A function that accepts X and y and returns a fitted model.
predictfcn: A function that accepts object and newdata and returns predictions.
eps: Convergence threshold.
iter.max: Maximum number of iterations.
verbose: If TRUE, prints progress messages.
...: Additional arguments passed to fitMethod.

An object of class backfitter.