Spearman correlation calculator

Check the rank relationship between two variables. Spearman works for ordinal scales, ratings, ranking positions and non-linear monotonic relationships.

Spearman correlation — a rank correlation coefficient that measures the relationship through the order of values rather than the values themselves.

Calculation FAQ

X,Y pairs

One pair per line, for example: 3, 7

Spearman rho

—

Result

rank correlation

Interpretation

Change the inputs to recalculate.

In SurveyNinja, NPS, CSAT and more are calculated automatically. Create a survey in 5 minutes and get real-time analytics.

Start free

Data is not stored — calculation runs in your browser.

How Spearman rho is calculated

Formula

X and Y values are converted to ranks, then the Pearson correlation between the ranks is calculated.

Ranks

The method looks at the order of values, so it is less sensitive to outliers than Pearson.

Monotonicity

Spearman detects a relationship when one variable generally rises with the other.

Range

rho runs from −1 to 1: the sign shows the direction, the absolute value shows the strength.

Calculation examples

1 Importance ranking and satisfaction

Importance: 1..7

Rating: 4, 5, 6, 6, 8, 9, 10

A positive rho shows that more important factors go together with higher ratings.

2 Feature priority rank and complaint frequency

Rank pairs by segment

Spearman checks whether two priority lists put things in the same order.

What to avoid

Looking only for a straight line Spearman is about monotonicity, not necessarily a linear relationship.
Reading causation Correlation does not prove that one factor causes the other.
Ignoring ties Equal values get average ranks. With many ties, interpret the result with care.

Frequently asked questions

How is Spearman different from Pearson?

Pearson measures a linear relationship between numeric values; Spearman measures the relationship between ranks and suits ordinal scales.

When should I use Spearman?

When the scale is ordinal, there are outliers, or the relationship is monotonic but not necessarily linear.

What does rho = 0.7 mean?

A strong positive rank relationship: higher values of X usually go with higher values of Y.

Can I use it on a 1–5 scale?

Yes. Spearman is well suited to ordinal ratings and rankings.

How many pairs do I need?

At least 3, but a reliable estimate of the relationship needs more observations.

All calculators

Automate your metrics