A little help goes a long way. Find a tool/

Math

Empirical Rule Calculator

Free empirical rule calculator: apply the 68-95-99.7 rule to any mean and standard deviation, with exact normal coverage for custom multiples like ±2.5σ. Runs in your browser.

YOUR WORKSPACEFree to use. No sign-up.
—
Enter a mean and standard deviation above.

Deep dive guides

A LITTLE CONTEXT · 4 MIN READThe 68-95-99.7 Rule Explained

How empirical rule calculator works

The empirical rule (also called the 68-95-99.7 rule or three-sigma rule) is a property of bell-shaped data: about 68% of values fall within one standard deviation of the mean, about 95% within two, and about 99.7% within three. Give the tool a mean and a standard deviation and it draws all three bands as concrete ranges — for heights averaging 170 cm with SD 7 cm, that is 163–177 cm, 156–184 cm, and 149–191 cm.

The word 'about' hides real precision, so each band also shows the exact normal-distribution coverage: 68.27%, 95.45%, and 99.73%, computed from the error function rather than the rounded mnemonic. The complements are shown too — 0.27% of data lies outside three standard deviations, which is why 3σ control limits dominate manufacturing: a process drifting beyond them is usually broken, not unlucky.

A custom multiple field lets you test any k: μ ± 1.96σ covers exactly 95.0004%, the source of the famous 1.96 in confidence intervals, and μ ± 2.5σ covers 98.76%. The rule belongs to roughly bell-shaped data — heights, measurement errors, exam averages of large classes — and misleads on skewed data like incomes, where the long tail pushes more than 0.3% beyond three standard deviations.

Frequently asked questions

What is the empirical rule?
For bell-shaped (normally distributed) data, about 68% of values lie within one standard deviation of the mean, about 95% within two, and about 99.7% within three. It is a quick way to sketch an entire distribution from just two numbers: mean and standard deviation.
How do I calculate the 68-95-99.7 ranges?
Take the mean and add/subtract the standard deviation once, twice and three times. For a mean of 100 and SD of 15: 85–115 (68%), 70–130 (95%), and 55–145 (99.7%). The exact normal coverage of those bands is 68.27%, 95.45% and 99.73%.
Why is 1.96 standard deviations special?
Because μ ± 1.96σ captures exactly 95% of a normal distribution. That is where the ±1.96 margin in 95% confidence intervals comes from — it is the z-multiple whose central band holds 95% of the curve.
When does the empirical rule fail?
On skewed data. Incomes, house prices and response times have long right tails: far more than 0.3% of values sit beyond three standard deviations. The rule assumes roughly symmetric, bell-shaped data — check a histogram or the mean-vs-median gap before trusting it.
What percentage is outside 3 standard deviations?
For exact normal data, 0.27% — about 3 in every 1,000 values. That tiny tail is the entire logic of statistical process control: if a stable 3σ process is producing more than a handful of outliers, something has actually changed in the process.