6 - Regression & Analysis Flashcards
What are the assumptions of regression?
- Linearity
- Homoscedasticity
- Normality of Residuals
- Independence
What is the assumption of linearity?
The relationship between X and the mean of Y is linear
What is the assumption of homoscedasticity?
The variance of the data should be approximately equal across the range of predicted values
What is the assumption of normality of residuals?
The residuals should be normally distributed
What is the assumption of independence?
Each observation should be independent of the others
True or False: Regression is sensitive to outliers.
True - but not all outliers are influential
What R function can be used to check all assumptions of linear regression? How do you know if an assumption has been violated?
gvlma() - if the p-value of an assumption is < 0.05, then the assumption is violated