ahaz.tune.control {ahaz}  R Documentation 
Tuning controls for regularization
Description
Define the type of tuning method used for regularization. Currently only used by tune.ahazpen
.
Usage
# Crossvalidation
cv.control(nfolds=5, reps=1, foldid=NULL, trace=FALSE)
# BICinspired
bic.control(factor = function(nobs){log(nobs)})
Arguments
nfolds 
Number of folds for crossvalidation. Default is

reps 
Number of repetitions of crossvalidation with

foldid 
An optional vector of values between 1 and 
trace 
Print progress of crossvalidation. Default is 
factor 
Defines how strongly the number of nonzero penalty parameters penalizes the score in a BICtype criterion; see the details. 
Details
For examples of usage, see tune.ahazpen
.
The regression coefficients of the semiparametric additive hazards
model are estimated by solving a linear system of estimating equations of the form
D\beta=d
with respect to \beta
. The natural loss function
for such a linear function is of the leastsquares type
L(\beta)=\beta' D \beta 2d'\beta.
This loss function is used for crossvalidation as described by Martinussen & Scheike (2008).
Penalty parameter selection via a BICinspired approach was described by
GorstRasmussen & Scheike (2011). With df
is the degrees of freedom and n
the number of
observations, we consider a BIC inspired criterion of the form
BIC = \kappa L(\beta) + df\cdot factor(n)
where \kappa
is a scaling constant included to remove dependency on the
time scale and better mimick the behavior of a ‘real’ (likelihood) BIC. The default factor=function(n){log(n)}
has
desirable theoretical properties but may be conservative in practice.
Value
An object with S3 class "ahaz.tune.control"
.
type 
Type of penalty. 
factor 
Function specified by 
getfolds 
A function specifying how folds are calculated, if applicable. 
rep 
How many repetitions of crossvalidation, if applicable. 
trace 
Print out progress? 
References
GorstRasmussen, A. & Scheike, T. H. (2011). Independent screening for singleindex hazard rate models with ultrahigh dimensional features. Technical report R201106, Department of Mathematical Sciences, Aalborg University.
Martinussen, T. & Scheike, T. H. (2008). Covariate selection for the semiparametric additive risk model. Scandinavian Journal of Statistics; 36:602619.