Variance Inflation Factor – How to Calculate VIF in Logistic Regression
logisticregressionvariance-inflation-factor
No book told me that…
Using McFadden’s Pseudo-R2 ? OR do traditional linear regression to get VIF?
Best Answer
The variance inflation factor is only about the independent variables. You can calculate it the same way in linear regression, logistic regression, Poisson regression etc.
Whether the same values indicate the same degree of "trouble" from colinearity is another matter. For this, I like to use the perturb package in R which looks at the practical effects of one of the main issues with colinearity: That a small change in the input data can make a large change in the parameter estimates.
The short answer is yes. Interaction terms tend to be collinear with the original variables involved. That is why post-hoc interaction tests are often underpowered.
Interaction that is unaccounted for renders the estimate wrong, while inflated variance inflates p-value. If the interaction terms are already statistically significant, inflation of variance is no longer a problem.
Can you use VIF with binary (0/1) variables? Why not? VIF only depends on the design matrix, and no distributional assumptions are needed!
Then the last question about variable selection. This is much discussed on this site, so search. The short answer is NO, the best approach is to select your variables before looking at the data. If that for some reason is impossible (to many variables, ...), then think about regularization. Otherwise, look through this list and especially Variable selection for predictive modeling really needed in 2016?
Best Answer
The variance inflation factor is only about the independent variables. You can calculate it the same way in linear regression, logistic regression, Poisson regression etc.
Whether the same values indicate the same degree of "trouble" from colinearity is another matter. For this, I like to use the
perturb
package inR
which looks at the practical effects of one of the main issues with colinearity: That a small change in the input data can make a large change in the parameter estimates.