One standard deviation is a specific distance from the average of a data set that captures roughly 68% of all values. If you picture a bell curve, one standard deviation marks the zone immediately surrounding the center, covering the majority of typical results. It’s the most common unit for describing how spread out numbers are, and it shows up in everything from test scores to stock prices.
How Standard Deviation Works
Standard deviation measures how far data points tend to sit from the average (the mean). A small standard deviation means most values cluster tightly around the average. A large one means values are scattered widely. One standard deviation is simply one “step” of that spread in either direction from the mean.
Think of it as a ruler built from the data itself. Every data set generates its own standard deviation, so the size of one “step” changes depending on what you’re measuring. For adult human height, one standard deviation is about 6.5 centimeters (roughly 2.5 inches). For IQ scores, it’s 15 points. The concept is the same in both cases: it tells you the range where most ordinary values fall.
The 68-95-99.7 Rule
When data follows a bell-shaped (normal) distribution, standard deviations carve it into predictable slices:
- Within 1 standard deviation of the mean: about 68% of all values
- Within 2 standard deviations: about 95% of all values
- Within 3 standard deviations: about 99.7% of all values
This pattern, sometimes called the empirical rule, is why one standard deviation matters so much. If someone tells you a value is “within one standard deviation,” they’re saying it falls in the fat middle of the bell curve, right where you’d expect most results to land. A value two or three standard deviations away is unusual, and beyond three is extremely rare.
Real-World Examples
Numbers get easier to grasp with concrete cases. Here are two that come up often.
Adult Height
A large meta-analysis of over one million people found that the average height for adult men is about 173 cm (5’8″) with a standard deviation of 6.5 cm. That means roughly 68% of men are between 166.5 cm and 179.5 cm tall, or about 5’5.5″ to 5’10.5″. A man who stands 186 cm (6’1″) is about two standard deviations above the mean, placing him taller than approximately 97.5% of the population.
IQ Scores
Standardized IQ tests are designed with a mean of 100 and a standard deviation of 15. So one standard deviation above the mean is a score of 115, and one below is 85. About 68% of people score between 85 and 115. A score of 130, two standard deviations above the mean, puts someone in roughly the top 2.5%.
How the Calculation Works
You don’t need to memorize a formula to understand standard deviation, but seeing the steps can make the concept click. The basic process has four parts:
- Find the mean of your data set.
- Subtract the mean from each data point, then square the result. Squaring removes negative signs so that values below the mean don’t cancel out values above it.
- Average those squared differences by adding them up and dividing by the number of data points.
- Take the square root of that average. This brings the number back into the original units (inches, points, dollars) instead of squared units.
The result is the standard deviation. One standard deviation equals that single number, measured in the same units as your original data.
One wrinkle worth knowing: when you’re working with a sample rather than an entire population, you divide by one less than the number of data points (n minus 1 instead of n). This small adjustment, known as Bessel’s correction, compensates for the fact that a sample tends to slightly underestimate the true spread of the whole population. In practice, most real-world calculations use this version because you’re almost never measuring every single member of a group.
What “High” and “Low” Standard Deviation Tell You
A standard deviation close to zero means nearly every value is almost identical to the average. Imagine a class where every student scored between 88 and 92 on a test. The standard deviation would be tiny, telling you that performance was very consistent.
Now imagine a class where scores ranged from 40 to 100. The standard deviation would be much larger, reflecting that wide gap between the lowest and highest performers. Neither situation is inherently good or bad. It depends on context. In manufacturing, a small standard deviation means parts are reliably uniform. In a stock portfolio, a large standard deviation signals higher volatility and risk.
Z-Scores: Measuring in Standard Deviations
Once you know the mean and standard deviation for a data set, you can express any individual value as a z-score. A z-score simply tells you how many standard deviations a value sits above or below the mean. A z-score of 1.0 means the value is exactly one standard deviation above average. A z-score of negative 2.0 means it’s two standard deviations below.
This is useful because it lets you compare values from completely different scales. A person who is one standard deviation taller than average and one standard deviation above the mean on an IQ test has a z-score of 1.0 in both cases, even though the raw numbers (179.5 cm and 115 points) look nothing alike. Z-scores translate everything into the same language of standard deviations.
Standard Deviation in Finance
In investing, standard deviation is the go-to measure of volatility. When a financial analyst says a stock has an annual standard deviation of 20%, they mean its returns typically swing about 20 percentage points above or below its average return in a given year. Higher standard deviation means wilder price swings and more risk. Lower standard deviation means steadier, more predictable performance.
Fidelity notes that rising standard deviation often accompanies market tops driven by nervous, indecisive traders, while falling standard deviation over long periods can signal a maturing bull market. At market bottoms, increasing volatility over short time frames typically reflects panic selling. Investors use these patterns to gauge whether price movements represent normal fluctuation or something more significant.