OLS · Diagnostics
Collinearity
When predictors overlap strongly, the model may have limited information to separate their conditional associations.
Page 1 of 7 · Big Picture
The big picture: Collinearity
Can the data distinguish the included predictors?
Why a policy analyst should care
When predictors contain little independent variation, coefficients become unstable and uncertain even if the model predicts the outcome reasonably well.
Follow the idea from the opening question to a practical decision. These are the conceptual moves this module will develop:
1 Question Can the data distinguish the included predictors?
2 Explore See uncertainty increase as predictors overlap
3 Formalize Collinearity concerns information, not morality
4 Transfer Defend a collinearity decision
Use the left and right arrow keys to move between pages.