What is the correlation coefficient?
The correlation coefficient r, also called Pearson’s r, measures the strength and direction of the straight-line link between two sets of paired numbers. It is always between −1 and 1. Values close to 1 or −1 mean the points sit close to a straight line; r = 1 or −1 means every point is on it.
The sign gives the direction: positive when y tends to rise as x rises, negative when it tends to fall. An r near 0 means there is little straight-line link, but look at the points too: a curve or a V shape can have r = 0. A strong correlation doesn’t mean x causes y.
How to calculate the correlation coefficient
Here it is with your numbers:
- There are 11 pairs, so the t test has 9 degrees of freedom (11 − 2).
- x̄ = 69.1818
- ȳ = 160.4545
- Σ(x − x̄)² = 81.6364
- Σ(y − ȳ)² = 4,326.7273
- Σ(x − x̄)(y − ȳ) = 394.0909
- r = 394.0909 ÷ √(81.6364 × 4,326.7273)
- r = 0.6631
- t = 0.6631 × √9 ÷ √(1 − 0.4397)
- t = 2.6576
- p = 0.0262 (both tails of the t distribution with 9 degrees of freedom)
It means the link is positive, and a sample this size would rarely show it if there were no link at all (p < 0.05).
The t test checks whether r is far enough from 0 for the number of pairs: t = r√(n − 2) ÷ √(1 − r²), with n − 2 degrees of freedom, and the p-value is the area in both tails of the t distribution beyond t.
Source NIST Dataplot Reference Manual · CORRELATION ↗OpenStax · Introductory Statistics 2e, 12.4 Testing the Significance of the Correlation Coefficient ↗
Correlation coefficient examples
| Data | r | p-value |
|---|---|---|
| Exam scores (11 students) | 0.6631 | 0.0262 |
| Dive depth and time | −0.9629 | 0.0020 |
| A V shape | 0 | 1 |
The exam scores and dive times are OpenStax’s examples. The V shape shows why r = 0 doesn’t mean “no relationship”: y follows x exactly, just not in a straight line.
FAQs
What is the formula for the correlation coefficient?
r = Sxy ÷ √(Sxx × Syy), where Sxy = Σ(x − x̄)(y − ȳ), Sxx = Σ(x − x̄)² and Syy = Σ(y − ȳ)². For the 11 exam scores, r = 394.0909 ÷ √(81.6364 × 4,326.7273), which is 0.6631.
Is r or r^2 the correlation coefficient?
r is the correlation coefficient. r² is the coefficient of determination: the share of the variation in y that the straight line explains. An r of 0.6631 gives an r² of 0.4397, so the line explains about 44% of it.
What is 0.7 correlation coefficient?
An r of 0.7 is a positive correlation: y tends to rise with x, and r² = 0.49, so the line explains 49% of the variation in y. Whether it is significant depends on the number of pairs: with 10 pairs the 5% critical value is 0.632, so 0.7 is significant; with 6 pairs it is 0.811, so 0.7 is not.
Is 0.5 a strong correlation coefficient?
There is no single cut-off. An r of 0.5 means the line explains 25% of the variation in y (r² = 0.25). Whether it is significant depends on the sample: with 14 pairs the 5% critical value is 0.532, so 0.5 is not significant; with more pairs it can be.
Sources
- NIST Dataplot Reference Manual: CORRELATION
- OpenStax: Introductory Statistics 2e, 12.3 The Regression Equation (the correlation coefficient r)
- OpenStax: Introductory Statistics 2e, 12.4 Testing the Significance of the Correlation Coefficient