Regression Analysis
- With Regression Analysis we focus on Cause and Effect kind of scenarios
- Correlation coeffecient: Correlations does not imply causation.
- Linear Regression: A linear regression is a linear approximation of causal relationship between two or more variables
- The above formuala is a population formula so, the sample formula is represented as
- Correlation vs Regression
Correlation | Regression |
---|---|
Relationship | One variable affects the other |
Movement together | Cause and effect |
p(x,y) = p(y,x) Two way | One way |
Represented by single point | Line |
- Geometrical representation of the linear regression
- Sample