optLambdas_mgcv {multiridge}

Find optimal ridge penalties with maximimum marginal likelihood

Description

Optimizes a marginal likelihood score w.r.t. ridge penalties for multiple data blocks.

Usage

optLambdas_mgcv(penaltiesinit=NULL, XXblocks,Y, pairing=NULL, model=NULL, reltol=1e-4,
  optmethod=ifelse(length(penaltiesinit)==1,"Brent", "Nelder-Mead"),maxItropt=500,
  tracescore=TRUE, fixedpen=NULL, fixedseed =TRUE, sigmasq = 1,
  opt.sigma=ifelse(model=="linear",TRUE, FALSE))

Arguments

penaltiesinit

Numeric vector. Initial values for penaltyparameters. May be obtained from fastCV2.

XXblocks

List of nxn matrices. Usually output of createXXblocks.

Y

Response vector: numeric, binary, factor or survival.

pairing

Numerical vector of length 3 or NULL when pairs are absent. Represents the indices (in XXblocks) of the two data blocks involved in pairing, plus the index of the paired block.

model

Character. Any of c("linear", "logistic", "cox"). Is inferred from Y when NULL.

reltol

Scalar. Relative tolerance for optimization methods.

optmethod

Character. Optimization method. Any of the methods c("Brent", "Nelder-Mead", "Sann") may be used, but "Nelder-Mead" is generally recommended. Other unconstrained methods offered by optim may also be used, but have not been tested.

maxItropt

Integer. Maximum number of iterations for optmethod.

tracescore

Boolean. Should the output of the scores be traced?

fixedpen

Integer vector or NULL. Contains indices of data types of which penalty is fixed to the corresponding value in penaltiesinit.

fixedseed

Boolean. Should the initialization be fixed? For reproducibility.

sigmasq

Default error variance.

opt.sigma

Boolean. Should the error variance be optimized as well? Only relevant for model="linear".

Details

See gam for details on how the marginal likelihood is computed.

Value

List, with components:

optres

Output of the optimizer

optpen

Vector with determined optimal penalties

allsc

Matrix with marginal likelihood scores for all penalty parameter configurations used by the optimizer

See Also

optLambdas_mgcvWrap for i) (recommended) optimization in two steps: first global, then local; and ii) sequential optimization when some data types are preferred over others. A full demo and data are available from:
https://drive.google.com/open?id=1NUfeOtN8-KZ8A2HZzveG506nBwgW64e4

Examples

data(dataXXmirmeth)
resp <- dataXXmirmeth[[1]]
XXmirmeth <- dataXXmirmeth[[2]]

# Find initial lambdas: fast CV per data block separately.
cvperblock2 <- fastCV2(XXblocks=XXmirmeth,Y=resp,kfold=10,fixedfolds = TRUE)
lambdas <- cvperblock2$lambdas

# Create (repeated) CV-splits of the data.
leftout <- CVfolds(Y=resp,kfold=10,nrepeat=3,fixedfolds = TRUE)

# Compute cross-validated score for initial lambdas
CVscore(penalties=lambdas, XXblocks=XXmirmeth,Y=resp,folds=leftout,
score="loglik")

# Optimize by using marginal likelihood criterion
jointlambdas2 <- optLambdas_mgcvWrap(penaltiesinit=lambdas, XXblocks=XXmirmeth,
Y=resp)

# Optimal lambdas
optlambdas <- jointlambdas2$optpen