Home/Calculators/Statistics/Covariance Calculator

Covariance Calculator

Find the population covariance of up to four paired data points, instant and free.

covariance-calculator
Result
—
In summary: Population covariance averages the product of each pair's deviations from their means. For x = 1, 2, 3, 4 and y = 2, 4, 6, 8 the deviation products sum to 10 over 4 pairs, so the covariance is 10 ÷ 4 = 2.5.

How to calculate covariance

Population covariance measures how two variables vary together. Subtract each variable's mean from its values, multiply the paired deviations, sum them, and divide by the number of pairs. For x = 1, 2, 3, 4 and y = 2, 4, 6, 8 the products of deviations sum to 10 over 4 pairs, so the covariance is 10 ÷ 4 = 2.5. The covariance of a variable with itself is simply its variance, which is a useful sanity check.

How to use this calculator

Enter up to four matching x and y pairs and leave unused rows blank. Both values of a pair must be filled to count. A positive result means the variables rise together; a negative one means they move oppositely. To standardize this into a −1 to +1 scale, see the correlation coefficient calculator.

Covariance vs. correlation

Covariance shows the direction of a relationship but its size depends on the units of the data. Correlation rescales covariance to a fixed −1 to +1 range, making strengths comparable. For relative spread of one variable, see the coefficient of variation calculator.

Frequently asked questions

How do I calculate covariance?
Multiply each pair's deviations from their means, sum the products, then divide by the number of pairs. For x = 1, 2, 3, 4 and y = 2, 4, 6, 8 the covariance is 2.5.
Is this population or sample covariance?
This calculator divides by n, giving the population covariance. Sample covariance would divide by n − 1.
What does a positive covariance mean?
It means the two variables tend to rise and fall together; a negative covariance means they move in opposite directions.
How is covariance different from correlation?
Covariance keeps the original units and has no fixed range, while correlation rescales it to between −1 and +1.
Does a covariance of zero mean the variables are unrelated?
Not necessarily — it only means there is no linear relationship. Two variables can be perfectly related in a curved pattern, such as y = x², and still return a covariance of zero. Plot the data before concluding that nothing connects them.
How this tool works

The formula behind this tool is written out in full in the sections above, so you can check the maths yourself. Every calculator on Calculorium is verified against worked examples with automated tests before it is published, and pages are reviewed as formulas or standards change. Nothing you type is sent anywhere — the calculation runs entirely in your browser. Read how we build and check these tools.

Last updated: July 27, 2026 · Calculations run in your browser. Estimates for information only.