σ Standard Deviation Calculator
Standard Deviation Calculator
Standard deviation measures spread: how far numbers typically stray from the average. A low value means the data clusters tightly; a high value means it is all over the place. It is the backbone of statistics, quality control and risk analysis.
Paste your numbers separated by commas, spaces or line breaks. You get both the population version (your data is everything) and the sample version (your data is a subset) — use sample when generalizing beyond the numbers you entered.
How to use this calculator
Paste your numbers into the box, separated by commas, spaces or line breaks. You get the mean, variance and standard deviation - both population and sample versions.
- Paste or type your numbers into the Numbers box, separating them with commas, spaces or line breaks.
- Enter at least two numbers - a single value has no meaningful spread.
- Press Calculate to see the mean, both standard deviations and both variances.
- Add or remove values and recalculate to watch how outliers move the standard deviation.
Worked example: the standard deviation of 2, 4, 4, 4, 5, 5, 7, 9
This is the exact table the calculator builds from your own numbers:
Step 1 — the mean: (2 + 4 + 4 + 4 + 5 + 5 + 7 + 9) ⁄ 8 = 40 ⁄ 8 = 5
Step 2 — every value’s deviation, squared:
| Value x | Deviation (x − 5) | Squared deviation |
|---|---|---|
| 2 | −3 | 9 |
| 4 | −1 | 1 |
| 4 | −1 | 1 |
| 4 | −1 | 1 |
| 5 | 0 | 0 |
| 5 | 0 | 0 |
| 7 | 2 | 4 |
| 9 | 4 | 16 |
| Sum | 32 |
Step 3 — variance: for a population, 32 ⁄ 8 = 4; for a sample, 32 ⁄ 7 ≈ 4.57
Step 4 — square root: population SD = √4 = 2; sample SD = √4.57 ≈ 2.14
Most of the values sit within one standard deviation of the mean: with a population SD of 2 the band runs from 3 to 7, which holds six of the eight values (the three 4s, the two 5s and the 7) — the spread here is moderate and even, exactly what the two results near 2 are saying.
What does this calculator report?
It summarizes any dataset: count, mean, population and sample variance, population and sample standard deviation, and the standard error of the mean. The mean is shown as the headline result.
How spread out is spread out?
Averages hide scatter. Two classes can both average 70% while one has every student between 65 and 75 and the other’s marks run from 30 to 100. The standard deviation is the typical distance between the values and their mean — the single number that tells those two classes apart. Small standard deviation: the values huddle near the mean. Large: they are scattered wide.
Population or sample — which one is yours?
If your numbers are everything there is — every student in the class, every day of last month — they are a population: divide by n. If they are a sample standing in for a bigger group you could not measure, divide by n − 1 instead. That small change is not pedantry: a sample tends to understate the true scatter, and dividing by n − 1 corrects for it, which is why the sample SD (2.14) comes out larger than the population SD (2) on the same data. The calculator prints both, so check the label before quoting either.
One more number: the standard error of the mean
The SEM answers a different question — not "how scattered are the values?" but "how precisely does the sample mean pin down the true mean?" For the example data it is 2.14 ⁄ √8 ≈ 0.76. SEM is the building block of confidence intervals and t-tests, so the calculator reports it alongside the standard deviations rather than making you work it out by hand.
Frequently asked questions
What is the standard deviation of 2, 4, 6, 8, 10?
The mean is 6 and the squared deviations add to 40. As a population: variance 40/5 = 8, SD ≈ 2.83. As a sample: variance 40/4 = 10, SD ≈ 3.16. The calculator shows both, with the full deviation table.
Why are there two answers — population and sample?
They answer for two different situations. Population SD describes a complete set of values. Sample SD estimates the spread of a larger group from a part of it, and divides by n − 1 to correct for the fact that samples understate scatter. Same data, two honest uses.
What does the squared-deviation table show me?
Exactly where the spread comes from. In the example, the two extreme values (2 and 10) contribute 16 + 16 = 32 of the total 40 — most of the "spread" in this dataset is really just its two ends. Squaring is what makes far-away values count for so much more than near ones.
What is the standard error of the mean, and how is it different from the SD?
The SD describes how much individual values vary. The SEM (sample SD ÷ √n, here ≈ 1.41) describes how much the mean itself would wobble if you repeated the sampling. More data shrinks the SEM but leaves the SD roughly where it is.
Can standard deviation be zero — or negative?
Zero, yes: if every value is identical, every deviation is 0 and the SD is 0. Negative, never: it is a square root of an average of squares, so the smallest it can be is zero.







































