stepPenal (version 0.2)

stepaic: Stepwise forward variable selection based on the AIC criterion

Description

It is a wrapper function over the step function in the buildin package stats

Usage

stepaic(Data, standardize = TRUE)

Arguments

Data

a data frame, as a first column should hava the response variable y

standardize

Logical flag for x variable standardization, prior to fitting the model sequence. Default is standardize=TRUE

Value

a list with the coefficients of the final model. It also returns the in-sample AUC and the Brier score

See Also

step

Examples

# NOT RUN {
set.seed(14)
beta    <- c(3, 2, -1.6, -4)
noise   <- 5
simData <- SimData(N=100, beta=beta, noise=noise, corr=FALSE)

stepaicfit <- stepaic(Data=simData)
stepaicfit
# }