Plot Method for Penalized Estimates With Cross-Validation

Plot the cross-validation performance or the coefficient path for fitted penalized elastic net S- or LS-estimates of regression.

# S3 method for class 'pense_cvfit'
plot(x, what = c("cv", "coef.path"), alpha = NULL, se_mult = 1, ...)

Arguments

x

fitted estimates with cross-validation information.

what

plot either the CV performance or the coefficient path.

alpha

If what = "cv", only CV performance for fits with matching alpha are plotted. In case alpha is missing or NULL, all fits in x are plotted. If what = "coef.path", plot the coefficient path for the fit with the given hyper-parameter value or, in case alpha is missing, for the first value in x$alpha.

se_mult

if plotting CV performance, multiplier of the estimated SE.

...

currently ignored.

See also

Other functions for plotting and printing: plot.pense_fit(), prediction_performance(), summary.pense_cvfit()

Examples

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

regpath <- pense(x, freeny$y, alpha = 0.5)
plot(regpath)


# Extract the coefficients at a certain penalization level
coef(regpath, lambda = regpath$lambda[[1]][[40]])
#>           (Intercept) lag.quarterly.revenue           price.index 
#>            -7.9064997             0.2125014            -0.7070107 
#>          income.level      market.potential 
#>             0.7141099             1.0796662 

# What penalization level leads to good prediction performance?
set.seed(123)
cv_results <- pense_cv(x, freeny$y, alpha = 0.5,
                       cv_repl = 2, cv_k = 4)
plot(cv_results, se_mult = 1)


# Extract the coefficients at the penalization level with
# smallest prediction error ...
coef(cv_results)
#>           (Intercept) lag.quarterly.revenue           price.index 
#>            -7.9064997             0.2125014            -0.7070107 
#>          income.level      market.potential 
#>             0.7141099             1.0796662 
# ... or at the penalization level with prediction error
# statistically indistinguishable from the minimum.
coef(cv_results, lambda = '1-se')
#>           (Intercept) lag.quarterly.revenue           price.index 
#>            -7.8652589             0.2141280            -0.7053433 
#>          income.level      market.potential 
#>             0.7126978             1.0754335