VIF - Variance Inflation Factor
Updated 2026-08-13
INTRODUCTION
English translation pending.
CORE DEFINITION
The variance inflation factor measures how much the variance of a regression coefficient is inflated because that predictor is collinear with the other independent variables. A common reading is that VIF above 10 signals severe multicollinearity, with 5 as an earlier warning line. When coefficients turn unstable or flip sign, checking VIF identifies exactly which variables are redundant duplicates of one another.
SCAFFOLDING EFFECT
Reduce cognitive load
- Collinearity alarm: unstable or sign-flipping coefficients should trigger a VIF check before anything else is concluded - Identifies the culprits: high-VIF variables reveal which predictors are redundant duplicates - Guides remediation: it tells you which variables to drop, merge, or regularize rather than guessing
Anchor fast decisions
When one predictor can be written almost as a combination of the others, its unique information shrinks while its estimated variance grows. VIF quantifies exactly that inflation, so a large value means the coefficient is being estimated from a thin slice of independent variation, which is precisely why it swings between samples.
MINIMUM ACTION
In progress 0/1Practice this model in one real situation:
account_treeGenealogyexpand_more
menu_bookReferencesexpand_more
Source support: Explicit
- en.wikipedia.orghttps://en.wikipedia.org/wiki/Variance_inflation_factorverified
PRIVATE NOTES · Only visible to you
SAVED Q&A
ENTRY Q&A · Private saving available
Ask with a clear boundary
thinkingmodels answers from published entry context only.
Your question is sent to thinkingmodels. The answer uses public entry context only.
RELATED MODELS