regularization {SSPA} | R Documentation |
Find optimal regularization parameter
regularization( b, A, beta, edf, lambda, z, method = c("lcurve", "gcv", "aic"), plot = TRUE, log = TRUE, verbose = FALSE )
b |
the b vector of the system: Ax = b. |
A |
the A matrix of the system: Ax = b. |
beta |
regression coefficients. |
edf |
effective degrees of freedom. |
lambda |
grid of penalty values. |
z |
intermediate matrix for L-curvature calculation. |
method |
Either the L-curve, GCV or AIC. |
plot |
Plot TRUE/FALSE. |
log |
Plot on log-scale TRUE/FALSE. |
verbose |
Verbose TRUE/FALSE |
details follow.
generates optionally figure and returns the index for the optimal penalty value.
Maarten van Iterson