Correlation Coefficient (r): What It Means and How to Calculate It
The correlation coefficient, usually Pearson’s r, measures how closely two variables follow a straight-line relationship. It runs from −1 to +1.
Quick answer
| r | Meaning |
|---|---|
| +1 | Perfect positive linear relationship |
| About +0.7 to +0.9 | Strong positive |
| About +0.3 to +0.7 | Moderate positive |
| Near 0 | Little or no linear relationship |
| Negative values | As one goes up, the other goes down |
| −1 | Perfect negative linear relationship |
The labels “strong” and “moderate” are rough guides; fields use different cut-offs.
The formula
r = Σ(x − x̄)(y − ȳ) ÷ √(Σ(x − x̄)² × Σ(y − ȳ)²)
It compares how x and y vary together with how much each varies on its own.
Worked example
Hours studied and test scores for six students:
| Hours (x) | Score (y) | x − x̄ | y − ȳ | (x − x̄)(y − ȳ) |
|---|---|---|---|---|
| 1 | 52 | -2.5 | -13.67 | 34.17 |
| 2 | 58 | -1.5 | -7.67 | 11.50 |
| 3 | 61 | -0.5 | -4.67 | 2.33 |
| 4 | 70 | 0.5 | 4.33 | 2.17 |
| 5 | 74 | 1.5 | 8.33 | 12.50 |
| 6 | 79 | 2.5 | 13.33 | 33.33 |
- Means: x̄ = 3.5, ȳ = 65.67.
- Σ(x − x̄)(y − ȳ) = 96.00; Σ(x − x̄)² = 17.50; Σ(y − ȳ)² = 533.33.
- r = 96.00 ÷ √(17.50 × 533.33) ≈ 0.994: a very strong positive relationship.
In Excel or Google Sheets
=CORREL(A1:A6, B1:B6) returns r. Squaring it gives r² (here 0.987), the share of the variation in y that a straight line through x explains.
Correlation isn’t causation
A high r doesn’t prove one thing causes the other. Ice-cream sales and sunburn cases are correlated, but both are driven by hot weather. Always ask whether a third factor could explain the link.
Other limits
- r only measures linear relationships; a perfect curve can have r near 0.
- One outlier can change r a lot; plot your data first.
- Small samples can show strong correlations by chance.
For related statistics, see standard deviation, variance and lines of the form y = mx + b.
Frequently asked questions
What does a correlation coefficient of 0.8 mean?
A strong positive linear relationship.
Can r be greater than 1?
No. It always lies between −1 and +1.
What does a negative correlation mean?
As one variable increases, the other tends to decrease.
Does correlation imply causation?
No. A third factor or coincidence may explain the link.
