VIF is calculated for each independent variable in a regression model. The formula for VIF is:
VIF = 1 / (1 - R²)
Here, R² represents the coefficient of determination from a regression of the independent variable against all other independent variables. A VIF value greater than 5 or 10 is often considered indicative of high multicollinearity, although the acceptable threshold can vary based on the specific context and field of study.