predict.grid_lasso: Predictions for continuous response model

In bgs25/SubsetGridRegression: Subset Grid Regression for Lasso, Ridge and Logistic Lasso Regression Models with Potential Prior Information

Description

Returns predicted response from grid lasso model with new data

Usage

## S3 method for class 'grid_lasso'
predict(
  object,
  newx,
  l = NULL,
  ll = NULL,
  missing.data = FALSE,
  psd.method = "enet",
  ...
)

Arguments

object	Object as returned by grid_lasso or cv_grid_lasso, provided return.list == T
newx	Design matrix for new observations
l	Specify grid point
ll	Specify point on lambda grid (optional)
missing.data	If TRUE then will use (slower) procedure that corrects for missing data, and will only return a (constant shifted) mean square error rather than actual predictions
psd.method	The way that the gram matrix is made positive semidefinite. By default an elastic net term, alternatives are "coco" for CoCoLasso
...	Additional arguments to pass to other predict methods

Value

Vector of predictions (or constant-shifted error if missing.data = TRUE)

bgs25/SubsetGridRegression documentation built on Dec. 19, 2021, 8:50 a.m.