← Back to Statistics
Correlation
Correlation Analysis
Measure association between two numeric variables.
Calculation engine
Client-side JavaScript; no external statistics package is loaded.
Results are calculated in the browser and are not uploaded.
Client-side JavaScript; no external statistics package is loaded.
Results are calculated in the browser and are not uploaded.
Method overview
When to use
Use Pearson correlation for linear continuous relationships and Spearman correlation for monotonic or ordinal relationships.
Input requirements
Enter X and Y vectors with the same number of values. At least 3 pairs are required.
Key assumptions
- Each X value is paired with one Y value.
- Pearson assumes an approximately linear relationship and no extreme outliers.
- Spearman uses ranks and is more robust for monotonic non-normal data.
Null hypothesis
H₀: the population correlation coefficient equals 0.
Method used
Pearson correlation; Spearman is Pearson correlation applied to ranks.
References
- Pearson K. Notes on regression and inheritance in the case of two parents. Proceedings of the Royal Society, 1895.
- Spearman C. The proof and measurement of association between two things. American Journal of Psychology, 1904.
Data input and results
Enter paired X and Y values in the same order. Variable names will be used as axis labels in the scatter plot.
No calculation has been performed.