VIF or 1/tolerance is a good measure of measuring multicollinearity in models. VIF is the percentage of the variance of a predictor which remains unaffected by other predictors. So higher the VIF value, greater is the multicollinearity amongst the predictors.

A rule of thumb for interpreting the variance inflation factor:

1 = not correlated.
Between 1 and 5 = moderately correlated.
Greater than 5 = highly correlated.

A commonly used metric for measuring the level of multicollinearity in a set of independent variables within a regression model is the Variance Inflation Factor (VIF). VIF assesses how much the variance of an estimated regression coefficient increases when the predictors are correlated.

The formula for VIF for a given variable is:

VIF(β^j)=1−Rj21

where $R_{j 2}$ is the coefficient of determination obtained by regressing the $j$ -th predictor against all the other predictors. A higher VIF indicates a higher degree of multicollinearity.

In practice, a VIF value of 1 indicates no multicollinearity, while values exceeding 5 or 10 are often considered concerning and may suggest the presence of significant multicollinearity. It’s essential to address multicollinearity issues as it can lead to unstable and unreliable estimates in regression models.