A variance inflation factor
(VIF) is obtained by regressing an independent variable on all of
the other explanatory (independent) variables in the analysis. The result is a term that is like the
coefficient of multiple determination (like an R-squared term). When no inter-corrleations exist the
coefficient of multiple determination is zero (0.0) and the VIF is at its lower
bound of one (1.0). When a variable
contributes to the correlation profile with other variables, the VIF increases
at an increasing rate towards infinity.
Variance inflation factors that exceed ten (10.0) are considered
problematic. A VIF of 10.0 or
higher is an indication that the variable has high and significant
multicollinearity with one or more of the other variables in the analysis.