standarddeviationcalculator.net

Updated Free · runs in your browser

Statistics

Variance and standard deviation calculator

One list of numbers, four answers: the sample variance and sample standard deviation, and the population variance and population standard deviation. The headline follows the mode you pick; the other mode's figure is printed underneath, and the SD is in the first row of results.

Separate numbers with commas, spaces or new lines, or paste a spreadsheet column. Decimals and negatives are fine; write 10:3 for a value that occurs 3 times.

Try:
Calculation type

Not sure which? How to choose sample or population

Variance (sample)

16.9444

The variance is in squared units, so it is hard to read on its own. Its square root is the standard deviation, 4.116: your values typically sit about that far above or below their mean of 28.78.

Population variance (σ²): 15.0617, if these values are the whole group.

Count (n)
9
Mean (x̄)
28.7778
Standard deviation (s)
4.11636
Standard error
1.37212
Minimum
22
Q1 (25%)
27
Median
29
Q3 (75%)
31
Maximum
35
Range
13
More statistics (5)
Relative SD (%RSD)
14.304%
Coefficient of variation
0.14304
Sum (Σx)
259
Sum of squares, Σ(x − x̄)²
135.556
IQR (Q3 − Q1)
4

Data distribution

20 25 30 35 40 mean 28.78 −1 SD +1 SD 24 — 1.16 SD below the mean31 — 0.54 SD above the mean28 — 0.189 SD below the mean35 — 1.51 SD above the mean22 — 1.65 SD below the mean30 — 0.297 SD above the mean27 — 0.432 SD below the mean33 — 1.03 SD above the mean29 — 0.054 SD above the mean Value

Shaded bands mark ±1, ±2 and ±3 SD from the mean. 5 of 9 values (56%) fall within ±1 SD.

Chart as text

Mean 28.7778, sample standard deviation s = 4.11636, from 9 values between 22 and 35.

  • Within ±1 SD (24.66 to 32.89): 5 of 9 values (56%). About 68% for normal data.
  • Within ±2 SD: 9 (100%). About 95% for normal data.
  • Within ±3 SD: 9 (100%). About 99.7% for normal data.
Show the working, step by step

All four figures for one data set

Nine commute times in minutes, 24, 31, 28, 35, 22, 30, 27, 33, 29, have a mean of 28.7778 and a sum of squared deviations Σ(x − x̄)² = 135.556. Everything else follows from those two numbers and the choice of denominator:

Variance (min²)Standard deviation (min)
Sample (÷ n − 1 = 8)s² = 16.9444s = 4.11636
Population (÷ n = 9)σ² = 15.0617σ = 3.88094

Read across a row and you move between variance and SD by squaring or rooting. Read down a column and you move between sample and population by rescaling by (n − 1)/n. Those are the only two relationships among the four.

The formulas side by side

s² = Σ(x − x̄)² / (n − 1) s = √s² σ² = Σ(x − μ)² / N σ = √σ²

Converting between sample and population without the raw data:

σ² = s² × (n − 1) / n s² = σ² × n / (n − 1)

For the commute data, 16.9444 × 8/9 = 15.0617, matching the table.

Units: why the variance looks so large

A variance of 16.9 next to a mean of 28.8 minutes can look alarming until you notice its units are minutes squared. It does not say commutes vary by 17 minutes; the SD says they typically vary by about 4. The same trap catches people with money: a variance in dollars² is not a dollar amount, and comparing it with a price is meaningless.

Units also explain why the variance is still used. Squared units add cleanly: if the drive to the station and the train ride vary independently, the variance of the whole journey is the sum of the two variances. That is what makes variance the working currency of ANOVA, regression and error propagation, while the SD is the number for people.

Choosing sample or population

If these nine commutes are a sample of the trips you will make this year, use s and s². If they are the only nine commutes you are describing — a week-and-a-bit you are reporting on and nothing more — use σ and σ². When in doubt, the sample version is the safer default, and the sample vs population guide explains the reasoning. Dedicated pages open in each mode: sample variance, population variance, sample SD and population SD.

For variance on its own, the variance calculator is the general tool; standard deviation vs variance covers when each is the right report.

Common questions

How do I convert variance to standard deviation?

Take the square root. A variance of 16.9444 min² is a standard deviation of √16.9444 = 4.11636 min. Going the other way, square the standard deviation.

Why is variance in squared units?

Because it averages squared deviations. If the data is in minutes, each deviation is in minutes and each squared deviation is in minutes squared. The square root in the standard deviation undoes that, which is why the SD is the one people quote.

Which of the four numbers should I report?

Usually the sample standard deviation, since most data is a sample and the SD is in the data's own units. Report a variance when it feeds into something else — an ANOVA table, a pooled estimate, a variance of a sum — and the population versions only when the data is the entire group.

Does the square root of the sample variance equal the sample SD?

Yes — the sample SD is defined as √s². The same holds for the population pair, σ = √σ². What you cannot do is mix them: the square root of the population variance is not the sample SD.

Can I add standard deviations?

Not directly. For independent quantities it is the variances that add: Var(X + Y) = Var(X) + Var(Y). Add the variances, then take the square root. Two independent steps with SDs of 3 and 4 minutes give a total SD of 5 minutes, not 7.