Definition
Correlation measures the strength and direction of a linear relationship between two quantities with a number from −1 to 1. Pearson's r works with the values and assumes a linear relationship; Spearman's ρ works with ranks and also captures monotonic nonlinear relationships. A value near 0 means no linear relationship, near ±1 an almost perfect one.
Statistical tests
Correlation is not causation: ice-cream sales correlate with drownings because both rise with temperature. It is also sensitive to outliers and to a restricted range of data — always inspect the relationship in a scatterplot; a single number can hide a curved relationship or two clusters.
With several variables you get a correlation matrix, best displayed as a matrix scatterplot or a heat map. The significance of a correlation (p-value) grows with sample size; the practical strength is expressed by r itself and its square — the share of shared variance.
In Statistica
Correlation matrices with p-values, scatterplots and matrix plots are in Statistics → Basic Statistics/Tables → Correlation matrices; Spearman, Kendall and gamma correlations are in Nonparametrics. Partial correlation (adjusted for other variables) is part of Multiple Regression.
Related terms
- Linear regressionLinear regression describes how a dependent variable (yield, price, consumption) depends on one or more explanatory…
- Effect sizeEffect size expresses how large a difference is or how strong an association is — independently of sample size.
- Nonparametric testsNonparametric tests do not assume a normal distribution — they work with the ranks of values rather than the values themselves.
- OutliersAn outlier is an observation that differs conspicuously from the rest — a measurement or entry error, a different population, or a genuine rare event.
Knowledgebase guides
FAQ
- How strong is a "strong" correlation?
- Roughly |r| ≥ 0.5 strong, 0.3 medium, 0.1 weak — but 0.9 is routine in engineering measurements and rare in social science. Follow your field's context.
- Pearson or Spearman?
- Pearson for continuous data with a linear relationship and no extremes; Spearman for ordinal data, monotonic nonlinear relationships or data with outliers.
Try it on your own data
Statistica free for 30 days
Full version, no credit card. Or get a pricing estimate in a minute.
Statistical tests
Updated: September 2026.