Linear Regression | What is Variance Inflation Factor ? How is it used?
Question
TheDataMonk
Follow Me
About TheDataMonkGrand Master
I am the Co-Founder of The Data Monk. I have a total of 6+ years of analytics experience 3+ years at Mu Sigma 2 years at OYO 1 year and counting at The Data Monk I am an active trader and a logically sarcastic idiot :)Follow Me
Answers ( 2 )
The variance inflation factor is defined as shown in the picture. Where Rj^2 is the R-squared from the auxiliary regression, i.e., a regression of all features except jth variable on the jth variable. The Matrix shows how does the inclusion of the given feature inflate the variance of our model.
The Variance Inflation Factor (VIF) is the measure of how much the variance of
the estimated regression coefficients are inflated as compared to when the
predictor variables are not linearly related. It helps in detecting multicollinearity.
VIF ranges from 1 upwards. A VIF of 1.5 tells you that the variance of a particular coefficient
is 50% bigger than what you would expect if there was no correlation with other predictors.
Generally, a VIF of 1 indicates no correlation
a VIF between 1 and 5 indicates that the variables are moderately correlated
a VIF of greater than 5 indicates high correlation between variables