Demystifying Standard Deviation and Its Relationship to Variance

Bar chart of six commute times, 22, 30, 26, 18, 34 and 26 minutes, with the mean of 26 and a shaded band one sample standard deviation (about 5.66 minutes) either side.

Variance and standard deviation both measure how spread out a data set is. Variance is the one used in most mathematical work; standard deviation is the one people usually report. This article explains how they are related and how to interpret a standard deviation.

The Mathematical Connection

  • Standard deviation is the square root of variance.
  • Variance is the square of standard deviation.

In symbols: σ = √σ² for a population, and s = √s² for a sample.

Why We Need Both

The answer is units. Variance is built from squared deviations, so its units are squared too. If you measure heights in inches, the variance is in square inches. A spread of “45 square inches” is hard to picture. Taking the square root returns to the original units: the standard deviation is in inches, which you can compare directly with the data.

Worked Example

Six commute times, in minutes: 22, 30, 26, 18, 34, 26. Treat them as a sample of a person’s typical commutes.

  1. The mean is 156 / 6 = 26.
  2. Deviations: −4, 4, 0, −8, 8, 0.
  3. Squared deviations: 16, 16, 0, 64, 64, 0. The sum of squares is 160.
  4. Sample variance: s² = 160 / 5 = 32 square minutes.
  5. Sample standard deviation: s = √32 ≈ 5.657 minutes.

“About 26 minutes, give or take about 6” is something anyone can understand; “a variance of 32 square minutes” is not. Both numbers describe the same spread.

Interpreting Standard Deviation

Roughly speaking, the standard deviation is a typical distance between a value and the mean. Strictly, it is the square root of the average squared distance, which gives more weight to large distances than a simple average would.

The 68-95-99.7 Rule

For data that follows a normal distribution (the bell curve), the standard deviation tells you a lot:

  • About 68% of values fall within ±1 standard deviation of the mean.
  • About 95% fall within ±2 standard deviations.
  • About 99.7% fall within ±3 standard deviations.

The rule does not apply to strongly skewed data, and six values are far too few to check whether data is normal. It is a guide for larger, roughly bell-shaped data sets.

Practical Uses

  • Investment volatility: returns with a higher standard deviation swing more from their average, which is one common measure of risk.
  • Grading: a teacher can see whether marks are tightly grouped or widely spread.
  • Manufacturing tolerances: engineers use standard deviation to check that parts stay within specification.

Summary

Variance is the average squared deviation; standard deviation is its square root, back in the original units. Use variance for calculations and standard deviation for describing results. The standard deviation calculator shows both, along with a chart of your data with the mean and a ±1 standard deviation band.

Back to Blog