Multiple Regression Flashcards
1
Q
Logic:
A
Is there reason to expect a causal relationship between the predictors and the response variable.
• Like Correlation, Regression can’t prove causation – that assumption is on us as the data collectors/owners.
2
Q
Fit:
A
Does the overall regression show a significant relationship between the predictors and the response variable?
3
Q
Parsimony:
A
Does each predictor contribute significantly to the explanation? Are some predictors not worth the trouble?
4
Q
Stability:
A
Are the predictors related to one another so strongly that regression estimates become erratic?
5
Q
Occam’s Razor
A
When two explanations are otherwise equivalent, we prefer the simpler one
6
Q
R2 Adjusted
A
- The closer R2 adjusted is to R2 the more each predictor is contributing
- The further apart the weaker the contributors
- R2 Adjusted will always be less than R2