Standard error
How much an average or a percentage typically moves by chance from sample to sample. For a percentage p measured on n people, it's the square root of p × (1 - p) ÷ n, so it shrinks only with the square root of the sample size.
In plain English
The standard deviation says how spread out individual values are; the standard error says how precisely you know their average. Quadrupling the sample only halves the standard error. That's why small groups produce extreme averages: their standard error is large, so they land at both ends of any ranking.
Uncle Gary explains
With a true turnover rate of 10%, the standard error is about 13 percentage points for an office of 5 and 2 points for an office of 200.
Why it matters for your money
A fund's average return over three years has a large standard error. Two funds whose three-year averages differ by a few points a year may not differ in skill at all.
Where we tested it
Related terms
All glossary terms. Educational content, not financial advice.