Pearson’s r Correlation Coefficient

As we fully understand that your statistical knowledge may have gone a little rusty, let us briefly recap Pearson’s r Correlation test.

When you carry out a Pearson’s Correlation test you calculate Pearsons’s Correlation coefficient r which is standardized form of the covariance. This coefficient is a measure of relationship and can have a value between -1 and + 1, with -1 a perfect negative relationship and + 1 a perfect positive relationship. If Pearson’s r = 0, no relationship exists at all.

When to use?

You may only use Pearson’s r as a measure of correlation if your data is continuous and meets parametric assumptions. If your data does not meet parametric assumptions you could calculate Spearman’s rho as a non-parametric alternative.

For both tests, any relationship found is significant (as in meaningful) when it has at least a 95% confidentiality level, which means that the probability value, also known as p-value is smaller than .05.

Typically, values of r = ± .1 are seen as a small effect size, r = ±. 3 as a medium effect size, and r = ± .5 as a large effect size.

Please note: Correlation does not imply Causation!

For more information on statistical tests, we refer you to the statistics manuals in the Recommended Reading of this module.