Skip to content
LoveToCalc

Definition — what does that mean?

Standard error of the mean

How much a sample mean would jump around if you drew the sample again — the uncertainty in the average itself.

In Swedish: Medelfel

Standard error of the mean

The relation

SE=Σ(xi−x)²n−1n

How much a sample mean typically varies from sample to sample: the sample standard deviation divided by the square root of the count.

Separate the numbers with spaces, commas or semicolons, for example 2.5, 4, 7

SE≈0.7559

SE equals the square root of (((2 minus 5) squared plus (4 minus 5) squared plus (4 minus 5) squared plus (4 minus 5) squared plus (5 minus 5) squared plus (5 minus 5) squared plus (7 minus 5) squared plus (9 minus 5) squared) divided by (8 minus 1)) divided by the square root of (8), is approximately the square root of (((−3) squared plus (−1) squared plus (−1) squared plus (−1) squared plus 0 squared plus 0 squared plus 2 squared plus 4 squared) divided by 7) divided by 2.8284, is approximately the square root of ((9 plus 1 plus 1 plus 1 plus 0 plus 0 plus 4 plus 16) divided by 7) divided by 2.8284, is approximately the square root of (32 divided by 7) divided by 2.8284, is approximately the square root of (4.5714) divided by 2.8284, is approximately 2.1381 divided by 2.8284, is approximately 0.7559

Working7 steps

The formula

SE = s / √n

s is the sample standard deviation and n the number of observations.

The sample 2, 4, 4, 4, 5, 5, 7, 9: the mean is 5, s = √(32 / 7) ≈ 2.138 and n = 8, so SE = 2.138 / √8 ≈ 0.7559.

The calculator takes the list itself and does all three steps.

Standard deviation and standard error answer different questions

s describes the data: a typical observation lies about 2.1 from the mean. SE describes the mean: if you took another eight observations from the same source, their mean would typically land about 0.76 from the true mean, and so would this one. The first stays roughly the same however much data you collect; the second shrinks.

Why n sits under a root

Averaging cancels out noise, but slowly. Four times as much data halves the standard error; a hundred times as much cuts it to a tenth. That is why the last digit of precision in a survey is so expensive — see sample size for a proportion.

n SE when s = 2.138
8 0.756
32 0.378
800 0.076

Where it is used

A confidence interval is the mean plus or minus a few standard errors, and the t-statistic is the distance to a hypothesised mean measured in standard errors.

Common mistakes

Questions people ask

Is “standard error” always about the mean? No — any estimate has one, such as a proportion or a regression slope. Without a qualifier it usually means the standard error of the mean.

Looking for another letter? The formula solved for each one
Solved for each letter
Solve forRearrangedWith the numbersComes to
SEΣ(xi−x)²n−1n(2−5)²+(4−5)²+(4−5)²+(4−5)²+(5−5)²+(5−5)²+(7−5)²+(9−5)²8−180.7559

Last reviewed September 26, 2026 ·How pages are reviewed

Statistics and probabilityAll formulas

Put this formula on your site

Copy the code into your page where the formula card should appear. It loads from lovetocalc.com, so it stays current on its own — all we ask is that the credit line comes with it.