How to Determine Linear Correlation

Highly vertical graphs correspond with strong correlations.

The linear correlation between two variables is the slope of the line joining the variables on a graph. A correlation close to "0" implies that the correlation between the variables, if any exists at all, is very small. A correlation of "1" suggests a strong correlation, and correlation could also be much higher and stronger. A highly negative slope also corresponds with a strong correlation, but this plot's variables would share an inverse relationship rather than a direct one.

Instructions

1. Identify two points on the linear graph that tracks the variables. For instance, two points may have coordinates of (3, 8) and (9, 9).

2. Subtract the first point's y coordinate from the second's: 9 - 8 = 1.

3. Subtract the first point's x coordinate from the second's: 9 - 3 = 6.

4. Divide the change in y between the two points by the the change in x: 1 ÷ 6 = 0.167. This is the correlation between the graph's variables.

References

• "Introductory Statistics: Concepts, Models, and Applications"; David W. Stockburger; 1998
• University of Utah: Equations and Graphs of Straight Lines

Resources

• West Texas A&M University: Graphing Linear Equations; Kim Seward; 2003
• Florida Institute of Technology: Point Slope Form of Line Equation; Priya Asokarathinam
• Rochester Institute of Technology: Graphing Linear Equations