Semipartial correlation calculator
Measure the unique relationship between X and Y after removing the effect of Z from X only.
Y and X residuals after controlling Z
The X axis shows the part of X not explained by Z; Y remains the full outcome variable.
Calculation components
| Measure | Value |
|---|---|
| Fill in the fields above — the result is computed on this page. | |
How do I use this page?
- Paste predictor X, outcome Y and control Z.
- Read sr and the unique contribution sr².
- Compare the result with raw and partial correlations.
What this page does not do: The tool removes one control variable Z from X only. It requires complete equal-length series and assumes linear relationships.
Further reading
Theory — what is semipartial correlation?
Semipartial correlation removes the linear effect of Z from predictor X only, then correlates the remaining part of X with the full variable Y. The squared coefficient, sr², shows the unique increase in explained variance of Y that comes from X beyond what Z already explains. This means the measure reflects only the distinct contribution of X, not the full variance explained by the model. sr² never equals the total variance explained by X and Z together.
Frequently asked questions
What does sr² mean?
Does the order of X and Y matter?
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.