Spearman’s rank correlation coefficient, often denoted as ρ (rho) or rₛ, measures the strength and direction of the monotonic relationship between two variables. A monotonic relationship is one where values tend to move consistently in the same direction, either increasing or decreasing, but not necessarily at a constant rate.
Spearman’s rank correlation coefficient is a nonparametric alternative to Pearson’s correlation coefficient. It is based on the ranks of the data rather than the raw values, making it more robust when data violate assumptions of normality or linearity. Analysts often use it when the relationship between variables is monotonic but not linear, or when the data are ordinal in nature.
The graph below displays a positive monotonic relationship.
To calculate Spearman’s rank correlation coefficient:
- Convert each variable’s data into ranks (with tied values assigned average ranks).
- Apply Pearson’s correlation formula to the ranked values.
The result ranges from –1 to +1:
- A value of +1 indicates a perfect increasing monotonic relationship.
- A value of –1 indicates a perfect decreasing monotonic relationship.
- A value near 0 suggests no consistent monotonic trend.
Unlike Pearson’s correlation, Spearman’s rank correlation coefficient does not assume interval-level measurement, linearity, or normally distributed variables. It is ideal when working with ordinal variables or when the relationship is not strictly linear but still consistently directional.
For example, a researcher collects survey data where participants rank their stress level and hours of sleep. Spearman’s correlation is –0.82, indicating a strong negative monotonic relationship: as stress ranks go up, sleep ranks go down.
« Back to Glossary Index