rvif_package

This repository has been created to control the rvif package. This package is focused on determining whether or not the degree of approximate multicollinearity in a multiple linear regression model is of concern, meaning that it affects the statistical analysis (i.e. individual significance tests) of the model.

This package uses functions from the multiColl package.

Historical

Previous versions: 1.0 and 3.0

Version 1:

Contains the functions "CV_VIF.R" and "RVIF.R"

Changes from version 1.0 to 2.0:

The function "Theorem.R" and data sets are added.

Changes from version 2.0 to 3.0:

Function names and arguments have been renamed and revised to improve usability. This package website has been added for easier access to documentation. A dedicated package homepage has been created, unit tests have been implemented for all functions and a vignette has been included to guide users in applying the package.

Changes from version 3.0 to 3.1:

Errors detected in the tests have been corrected.

Changes from version 3.1 to 3.2:

cv_vif_plot() has been replaced with an S3 method plot.cv_vif().

Current version: 3.2

Instalation

You can install the stable version from CRAN (recommended):

> install.packages("rvif", dependencies = TRUE)

You can install the development version from Github:

> install.packages("remotes")
> 
> remotes::install_github("rnoremlas/rvif")

Data

This package has the following datasets available:

Usage

> library(rvif)
>
> 
> x = euribor[, -1]
> 
> cv_vif(x)
> 
> plot(cv_vif(x))
> abline(h=10, col="red", lwd=3, lty=2)
> abline(h=0, col="black", lwd=1)
> abline(v=0.1002506, col="red", lwd=3, lty=3)
>
> 
> rvifs(x)
>
> 
> y = euribor[, 1]
> 
> multicollinearity(y, x)
> 
> multicollinearity(y, x, alpha = 0.01)

For more information

License

This package is free and open source software, licensed under GPL-3.