Mathematics
Empirical Rule (68-95-99.7 Rule)
Quick fact
The empirical rule is also known as the 'three-sigma rule' because it focuses on intervals of one, two, and three standard deviations (sigma) from the mean.
Why this is interesting
If you know the average height of a group of people, can you guess how many are within a few inches of that average? The empirical rule gives a surprisingly precise answer—as long as the data follows a bell-shaped curve.
Read the full explanation
Understanding Empirical Rule (68-95-99.7 Rule)
Imagine you have a large set of data—like test scores in a big class—that forms a symmetric bell-shaped curve (a normal distribution). The center of the curve is the average (mean). The curve spreads out; how far it spreads is measured by standard deviation. The empirical rule says: about 68% of all scores lie within one standard deviation of the mean (one step left or right). About 95% are within two standard deviations, and nearly all (99.7%) are within three. So if the average is 70 and the standard deviation is 10, then 68% of scores are between 60 and 80, 95% between 50 and 90, and 99.7% between 40 and 100. This rule only works for data that is approximately normal—not all distributions behave this way.
A deeper explanation
The empirical rule is a direct consequence of the mathematical properties of the normal distribution, defined by its probability density function. The area under the curve between any two points corresponds to the proportion of data in that interval. Using calculus, the integrals of the normal curve yield these precise percentages (68.27%, 95.45%, 99.73%). The rule is fundamental in statistics for quickly estimating probabilities, checking assumptions (e.g., if data is normal), and flagging potential outliers (values beyond three standard deviations are rare). It also underlies quality control charts (e.g., six-sigma methods) and risk assessment in finance. However, it should not be blindly applied to skewed or multimodal distributions—always verify normality first.