Mean, median and standard deviation calculator
Paste a list of numbers and get mean, median, standard deviation, min, max and sum.
How the calculation works
These measures summarize a set of numbers. The three most used:
- Mean: add everything and divide by the count — the data's "center of gravity".
- Median: sort the values and take the middle one (average of the two middle if even). It is not distorted by extremes.
- Standard deviation: how much the data spread around the mean.
Sample standard deviation:
s = √( Σ(x − mean)² ÷ (n − 1) )
Step-by-step example (4, 8, 15, 16, 23, 42)
- Mean: 108 ÷ 6 = 18
- Median: middle two are 15 and 16 → 15.5
- Deviation: high here (~13.3), values range from 4 to 42
Mean or median?
With outliers, the median better represents the "typical" value. That's why incomes and house prices are usually reported by the median.
What the standard deviation tells you
Low = data clustered near the mean (consistent). High = spread out. Two classes can share a mean grade but differ wildly in spread.
Examples
- Grades 7, 8, 9: mean 8, median 8, deviation 1.
- With an outlier (7, 8, 9, 50): the mean jumps to 18.5, but the median stays at 8.5.
Frequently asked questions
Sample or population standard deviation?
We use the sample one (divides by n−1), the most common in applied statistics.
Standard deviation vs variance?
Variance is the average of squared deviations; standard deviation is its square root, preferred because it shares the data's unit.
When to use median over mean?
When extreme values distort the mean — income, house prices, response times. The median better represents the "typical" value.
Related calculators
More Statistics calculators
See all →Combinations & permutations
Calculate combinations C(n,r), arrangements P(n,r) and the factorial from n and r.
Probability
Calculate the probability of an event from the favorable cases and the total possible cases.
Sample size
Find out how many people to survey based on margin of error and confidence level.
Updated on June 18, 2026 · by Rafael Rossi · Methodology & sources