Partial correlation calculator
Measure the linear relationship between X and Y after statistically removing the effect of one control variable Z.
X and Y residuals after controlling Z
Each point shows what remains of X and Y after their linear relationship with Z is removed.
Coefficient comparison
| Coefficient | Value |
|---|---|
| Fill in the fields above — the result is computed on this page. | |
How to use this page
- Paste X, Y and Z in matching observation order.
- Compare raw and partial correlations.
- Inspect the residual plot and possible outliers.
What this page does not do: All series must have equal length and variation. The model controls one variable and describes linear relationships only.
Further reading
Partial correlation answers how strongly X and Y are linearly related after the effect of Z is removed from both variables. The calculator regresses X on Z and Y on Z, then calculates Pearson correlation between the two residual series.
Compare the result with the raw correlation. A large difference suggests that Z accounts for part of the observed relationship. This remains a measure of association and does not establish causation.
Frequently asked questions
How does partial correlation differ from ordinary correlation?
Ordinary correlation uses raw X and Y. Partial correlation removes the linear effect of Z from both variables.
Does a high partial correlation prove causation?
No. It shows an association after controlling Z but does not rule out other variables or reverse causation.
See also
A/B test calculator
Compare two proportions in an A/B test. Calculate conversion rates, difference, uplift, z score, p value and c
A/B test planning — sample size, MDE and duration
Plan a two-proportion experiment, estimate detectable effect and traffic duration.
ACF and PACF autocorrelation calculator
Calculate ACF and PACF across time-series lags. Review the chart, reference bounds and coefficient table.