Sample Correlation Calculator

Compute Pearson correlation from paired values instantly. Inspect tables, trend lines, sample statistics, and assumptions. Download clean outputs for dashboards, research notes, and presentations.

Enter paired data

Use one X,Y pair per line. Commas, spaces, tabs, or semicolons are accepted.

Paired observations

Example row: 12.5, 18.2

Invalid line handling Decimal places Confidence level

Quick actions

Use the sample dataset to test the calculator instantly and review every output block.

Show scatter plot and trend line

Example data table

This sample shows steadily increasing paired values with a strong positive association.

Observation	X Value	Y Value
1	2	5
2	4	7
3	5	8
4	6	9
5	8	10
6	9	12
7	11	14
8	12	15

Formula used

The calculator applies the Pearson sample correlation formula and supporting sample statistics for covariance, linear regression, significance testing, and confidence intervals.

Sample correlation:

r = Σ[(x_i − x̄)(y_i − ȳ)] / √{Σ(x_i − x̄)² · Σ(y_i − ȳ)²}

Sample covariance:

cov(x,y) = Σ[(x_i − x̄)(y_i − ȳ)] / (n − 1)

Regression line:

ŷ = a + bx, where b = Σ[(x_i − x̄)(y_i − ȳ)] / Σ(x_i − x̄)² and a = ȳ − bx̄

Significance test for correlation:

t = r √[(n − 2) / (1 − r²)], with degrees of freedom n − 2. Confidence limits use Fisher’s z transformation.

How to use this calculator

Paste one paired observation per line in the data box.
Choose whether invalid rows should be omitted or flagged.
Select the number of decimal places and confidence level.
Optionally enable the scatter plot and trend line view.
Press the calculate button to show the result block above the form.
Review correlation strength, regression output, p value, and the detailed table.
Use the export buttons to download a CSV file or PDF report.

FAQs

1. What does the sample correlation value measure?

It measures the strength and direction of a linear relationship between two numeric variables. Values near 1 or −1 indicate stronger linear association, while values near 0 indicate little linear relationship.

2. When should I use sample correlation instead of covariance?

Use correlation when you want a standardized measure between −1 and 1. Covariance depends on the units of both variables, which makes comparisons across datasets harder.

3. Can this calculator handle missing or invalid rows?

Yes. You can omit incomplete rows automatically or stop the analysis and display line level issues. This helps when working with pasted data from spreadsheets or reports.

4. Why does the calculator show a regression line too?

Correlation describes association, while the regression line summarizes the best linear prediction of Y from X. Showing both helps you interpret slope, fit quality, and prediction direction together.

5. What does the p value represent here?

The p value tests the null hypothesis that the population correlation equals zero. Smaller values suggest the observed linear association is unlikely to be explained by sampling variation alone.

6. Why is a confidence interval for rho useful?

It gives a plausible range for the population correlation, not just the sample estimate. Narrower intervals suggest more precision, while wider intervals indicate greater uncertainty from limited data.

7. Why would the calculator reject my dataset?

A valid result needs at least three numeric pairs and variation in both variables. If one series is constant or too many lines are invalid, the correlation formula becomes undefined.

8. Does a high correlation mean causation?

No. Correlation only quantifies association. Strong relationships can still be driven by confounding variables, trends over time, measurement artifacts, or coincidence rather than direct causal influence.