Tangled Predictors
Each row of X holds the predictors of one observation. Return the variance inflation factor of each column, in order: 1 when a predictor is unrelated to the others, large when the others nearly determine it. Compute them with an intercept in the model.
Example 1
X [[1,5],[2,3],[3,4],[4,1],[5,2],[6,6],[7,0],[8,7]]
returns [1.0051282051282049,1.005128205128205]
The two columns have little to do with each other, so both factors are close to 1.
Example 2
X [[1,2],[2,4.1],[3,5.9],[4,8.2],[5,9.8],[6,12.1],[7,14],[8,15.9]]
returns [1456.5845511481273,1456.5845511481273]
The second column is almost exactly twice the first, so both factors are huge.
Constraints
Xhas 2 or 3 columns and 8 to 40 rows- No column is an exact combination of the others
Write it in your browser, against the clock. The model solution, stepped through line by line, comes after.
More statsmodels problems
- Top of the CurveMedium
- Trust Some Points MoreMedium
- Uneven SpreadMedium
- Do the Effects CombineHard
- Drop the Weak OnesHard
- Effect of the ProgramHard
- Enough PeopleHard
- Honest ErrorHard