How jumpy are these investment returns
Two funds both averaged 8 percent a year over five years, but one swung between -10 and +25 while the other sat calmly near 8 every year. The average hides the whole story. Variance is the statistic that measures spread: how far the numbers typically stray from their average. High variance means wild swings; low variance means steady, predictable values.
The variance formulas
Formula: Population variance = sum of (x - mu)^2 / N. Sample variance = sum of (x - xbar)^2 / (n - 1).
Each x is a data value, mu (or xbar) is the mean, and N (or n) is the count. You subtract the mean from each value, square each difference so negatives do not cancel, add them up, and divide. Use the population version when your data is the entire group of interest; use the sample version, dividing by n - 1, when your data is a sample drawn from a larger group, because the sample mean slightly underestimates the true spread.
How to use this calculator
- Enter your data values.
- Choose population if the data is everything, or sample if it is a subset.
- Run the calculation to see each squared deviation and the final variance.
- Compare variances across data sets to judge which is more spread out.
Worked example
Data: 2, 4, 6, 8, 10. Step 1: find the mean, (2 + 4 + 6 + 8 + 10) / 5 = 30 / 5 = 6. Step 2: subtract the mean from each value: -4, -2, 0, 2, 4. Step 3: square each: 16, 4, 0, 4, 16. Step 4: add them, 16 + 4 + 0 + 4 + 16 = 40. Step 5: population variance = 40 / 5 = 8; sample variance = 40 / 4 = 10. The sample version is larger because dividing by n - 1 corrects for the smaller sample.
Where this comes in handy
Investors read variance as risk, manufacturers use it to keep parts within tolerance, teachers compare how spread out test scores are between classes, and scientists check whether an experiment is consistent enough to trust. Anywhere consistency matters, variance is the number people quote.
Mistakes people often make
- Using the population formula on sample data. When in doubt with real-world samples, use n - 1.
- Forgetting to square the deviations. Without squaring, the positives and negatives cancel to zero every time.
- Reporting variance in the original units. Variance is in squared units; take the square root to get back to the original scale.
What this number does not tell you
Variance is sensitive to outliers: one extreme value can dominate the whole result. It also says nothing about the shape of the data; two very different distributions can share the same variance. Always look at the data itself, not just the summary number.
More statistics tools? The mean calculator finds the average first, the standard deviation calculator converts variance back to original units, and the covariance calculator compares two data sets at once.