R Regression: multicollinearity essentials and vif

1. Ref: http://www.sthda.com/english/articles/39-regression-model-diagnostics/160-multicollinearity-essentials-and-vif-in-r/

library(tidyverse)
library(caret)

# Load the data
data("Boston", package = "MASS")
# Split the data into training and test set
set.seed(123)
training.samples <- Boston$medv %>%
  createDataPartition(p = 0.8, list = FALSE)
train.data  <- Boston[training.samples, ]
test.data <- Boston[-training.samples, ]

# Build the model
model1 <- lm(medv ~., data = train.data)
# Make predictions
predictions <- model1 %>% predict(test.data)
# Model performance
data.frame(
  RMSE = RMSE(predictions, test.data$medv),
  R2 = R2(predictions, test.data$medv)
)

# Detecting multicollinearity
car::vif(model1)

# Dealing with multicollinearity
# Build a model excluding the tax variable
model2 <- lm(medv ~. -tax, data = train.data)
# Make predictions
predictions <- model2 %>% predict(test.data)
# Model performance
data.frame(
  RMSE = RMSE(predictions, test.data$medv),
  R2 = R2(predictions, test.data$medv)
)

Referensi

• http://www.sthda.com/english/articles/39-regression-model-diagnostics/160-multicollinearity-essentials-and-vif-in-r/

Pranala Menarik

• R