FitRidge: Perform ridge regression

In martindurocher/floodRFA: A R-package for regional frequency of floods

Description

Wrapper for the ridge regression function in MASS package to use with predict and residuals function. Prediction are obtained using the best regularization values.

Usage

FitRidge(form, x, lambda = seq(0, 0.1, 0.001))

## S3 method for class 'ridgelm'
predict(obj, xnew = NULL, optim = "gcv")

## S3 method for class 'ridgelm'
residuals(obj, ...)

Arguments

form	Formula of the model
x, xnew	Data frame of the data
lambda	List of regularization value
optim	Criteria to choose the best lambda

Examples

 # Example from MASS package
longley # not the same as the S-PLUS dataset
names(longley)[1] <- "y"

fit <- FitRidge(y ~ ., longley, lambda = seq(0,0.1,0.001))

plot(fit)
select(fit)
plot(predict(fit), residuals(fit))
abline( h = 0)

martindurocher/floodRFA documentation built on June 5, 2019, 8:44 p.m.