predict.pense_cvfit: Predict Method for PENSE Fits

Description

Predict response values using a PENSE (or LS-EN) regularization path with hyper-parameters chosen by cross-validation.

Usage

# S3 method for pense_cvfit
predict(
  object,
  newdata,
  alpha = NULL,
  lambda = "min",
  se_mult = 1,
  exact = deprecated(),
  correction = deprecated(),
  ...
)

Value

a numeric vector of residuals for the given penalization level.

Arguments

object: PENSE with cross-validated hyper-parameters to extract coefficients from.
newdata: an optional matrix of new predictor values. If missing, the fitted values are computed.
alpha: Either a single number or NULL (default). If given, only fits with the given alpha value are considered. If lambda is a numeric value and object was fit with multiple alpha values and no value is provided, the first value in object$alpha is used with a warning.
lambda: either a string specifying which penalty level to use ("min", "se", "{m}-se") or a single numeric value of the penalty parameter. See details.
se_mult: If lambda = "se", the multiple of standard errors to tolerate.
exact: deprecated. Always gives a warning if lambda is not part of the fitted sequence and coefficients are interpolated.
correction: defunct.
...: currently not used.

Hyper-parameters

If lambda = "{m}-se" and object contains fitted estimates for every penalization level in the sequence, use the fit the most parsimonious model with prediction performance statistically indistinguishable from the best model. This is determined to be the model with prediction performance within m * cv_se from the best model. If lambda = "se", the multiplier m is taken from se_mult.

By default all alpha hyper-parameters available in the fitted object are considered. This can be overridden by supplying one or multiple values in parameter alpha. For example, if lambda = "1-se" and alpha contains two values, the "1-SE" rule is applied individually for each alpha value, and the fit with the better prediction error is considered.

In case lambda is a number and object was fit for several alpha hyper-parameters, alpha must also be given, or the first value in object$alpha is used with a warning.

Examples

Run this code

# Compute the LS-EN regularization path for Freeny's revenue data
# (see ?freeny)
data(freeny)
x <- as.matrix(freeny[ , 2:5])

regpath <- elnet(x, freeny$y, alpha = 0.75)

# Predict the response using a specific penalization level
predict(regpath, newdata = freeny[1:5, 2:5],
        lambda = regpath$lambda[[1]][[10]])

# Extract the residuals at a certain penalization level
residuals(regpath, lambda = regpath$lambda[[1]][[5]])

# Select penalization level via cross-validation
set.seed(123)
cv_results <- elnet_cv(x, freeny$y, alpha = 0.5,
                       cv_repl = 10, cv_k = 4)

# Predict the response using the "best" penalization level
predict(cv_results, newdata = freeny[1:5, 2:5])

# Extract the residuals at the "best" penalization level
residuals(cv_results)
# Extract the residuals at a more parsimonious penalization level
residuals(cv_results, lambda = "1.5-se")