R: ENPY Initial Estimates for EN S-Estimators

enpy_initial_estimates {pense}

R Documentation

ENPY Initial Estimates for EN S-Estimators

Description

Compute initial estimates for the EN S-estimator using the EN-PY procedure.

Usage

enpy_initial_estimates(
  x,
  y,
  alpha,
  lambda,
  bdp = 0.25,
  cc,
  intercept = TRUE,
  penalty_loadings,
  enpy_opts = enpy_options(),
  mscale_opts = mscale_algorithm_options(),
  eps = 1e-06,
  sparse = FALSE,
  ncores = 1L
)

Arguments

`x`	`n` by `p` matrix of numeric predictors.
`y`	vector of response values of length `n`.
`alpha`	elastic net penalty mixing parameter with `0 \le \alpha \le 1`. `alpha = 1` is the LASSO penalty, and `alpha = 0` the Ridge penalty. Can be a vector of several values, but `alpha = 0` cannot be mixed with other values.
`lambda`	a vector of positive values of penalization levels.
`bdp`	desired breakdown point of the estimator, between 0.05 and 0.5. The actual breakdown point may be slightly larger/smaller to avoid instabilities of the S-loss.
`cc`	cutoff value for the bisquare rho function. By default, chosen to yield a consistent estimate for the Normal distribution.
`intercept`	include an intercept in the model.
`penalty_loadings`	a vector of positive penalty loadings (a.k.a. weights) for different penalization of each coefficient. Only allowed for `alpha` > 0.
`enpy_opts`	options for the EN-PY algorithm, created with the `enpy_options()` function.
`mscale_opts`	options for the M-scale estimation. See `mscale_algorithm_options()` for details.
`eps`	numerical tolerance.
`sparse`	use sparse coefficient vectors.
`ncores`	number of CPU cores to use in parallel. By default, only one CPU core is used. Not supported on all platforms, in which case a warning is given.

Details

If these manually computed initial estimates are intended as starting points for pense(), they are by default shared for all penalization levels. To restrict the use of the initial estimates to the penalty level they were computed for, use as_starting_point(..., specific = TRUE). See as_starting_point() for details.

References