Statistics Standard Deviation Equation- Complete Guide
What Standard Deviation Actually Is
Standard deviation measures how spread out numbers are from their average (mean). A low standard deviation means numbers cluster close together. A high standard deviation means they spread out widely.
That's it. That's the whole concept.
You encounter this everywhere: finance uses it to gauge investment volatility, manufacturers use it for quality control, scientists use it to validate experiments. If data has variance, standard deviation is probably involved.
The Standard Deviation Equation
There are actually two formulas depending on whether you're working with an entire population or just a sample.
Population Standard Deviation
Use this when you have every single data point available.
σ = √[Σ(xi - μ)² / N]
Where:
- σ = population standard deviation
- xi = each individual value
- μ = population mean
- N = total number of values
- Σ = sum of all values
Sample Standard Deviation
Use this when your data is just a sample from a larger group.
s = √[Σ(xi - x̄)² / (n-1)]
Where:
- s = sample standard deviation
- xi = each individual value
- x̄ = sample mean
- n = sample size
Notice the (n-1) in the denominator. This is Bessel's correction. It corrects the bias that occurs when estimating population parameters from a sample.
Population vs Sample: When to Use Which
This distinction matters. Using the wrong formula gives you wrong results.
| Scenario | Formula | Why |
|---|---|---|
| Every data point known | Population (N) | You have the complete dataset |
| Sample from larger group | Sample (n-1) | Estimating true population spread |
| Quality testing all products | Population | Entire batch measured |
| Surveying voters for election | Sample | Cannot ask every voter |
How to Calculate Standard Deviation (Step by Step)
Let's work through an example. Test scores: 70, 80, 85, 90, 95
Step 1: Find the Mean
Add all values and divide by count.
(70 + 80 + 85 + 90 + 95) ÷ 5 = 84
Step 2: Find Each Deviation from the Mean
Subtract the mean from each value:
- 70 - 84 = -14
- 80 - 84 = -4
- 85 - 84 = +1
- 90 - 84 = +6
- 95 - 84 = +11
Step 3: Square Each Deviation
- (-14)² = 196
- (-4)² = 16
- (1)² = 1
- (6)² = 36
- (11)² = 121
Step 4: Sum the Squared Deviations
196 + 16 + 1 + 36 + 121 = 370
Step 5: Divide by N (or n-1)
370 ÷ 5 = 74 (for population)
Step 6: Take the Square Root
√74 = 8.6
The standard deviation is 8.6 points. Most scores fall within 8.6 points of the mean (84).
Quick Reference: Variance vs Standard Deviation
Variance is the standard deviation squared. Some fields prefer variance because it has nice mathematical properties. But standard deviation is more intuitive since it uses the same units as your original data.
| Measure | Formula | Units |
|---|---|---|
| Population Variance | σ² = Σ(xi - μ)² / N | Squared original units |
| Population Std Dev | σ = √[Σ(xi - μ)² / N] | Same as original data |
| Sample Variance | s² = Σ(xi - x̄)² / (n-1) | Squared original units |
| Sample Std Dev | s = √[Σ(xi - x̄)² / (n-1)] | Same as original data |
How to Calculate in Excel or Google Sheets
You don't need to do this manually. Spreadsheets have built-in functions.
- Population std dev: =STDEV.P(range)
- Sample std dev: =STDEV.S(range)
- Variance: =VAR.P(range) or =VAR.S(range)
Most beginners confuse STDEV with STDEVP. Check which one you need.
Common Mistakes That Ruin Your Calculation
Using sample formula on population data. This inflates your result slightly. Not catastrophic, but unnecessary.
Forgetting to square the deviations. The negatives and positives cancel out, giving you zero every time. Squaring fixes this.
Using n instead of n-1 for samples. Your estimate of population spread will be biased low. With small samples (n < 30), this error is significant.
Rounding too early. Keep full precision through calculations. Round only at the end.
Real-World Applications
Finance: A stock with 20% annual return and 15% standard deviation is more volatile than one with 20% return and 5% standard deviation. Higher std dev = more risk.
Manufacturing: If bolt diameters have a standard deviation of 0.02mm, most production falls within that range. Anything outside signals a process problem.
Test scores: SAT scores are scaled so the mean is 1050 and standard deviation is 100. This lets you compare how unusual any specific score is.
Weather: Two cities might average 75°F in summer, but one has a std dev of 5° (consistent) while another has 20° (wild swings between heat waves and cool spells).
The Empirical Rule (68-95-99.7)
For normally distributed data:
- 68% of values fall within 1 standard deviation of the mean
- 95% of values fall within 2 standard deviations
- 99.7% of values fall within 3 standard deviations
This only applies when your data roughly follows a bell curve. Check your distribution first.
When Standard Deviation Misleads You
Standard deviation assumes symmetry around the mean. With skewed data (like income distribution), it tells an incomplete story. A few billionaires will inflate the standard deviation of salaries, making typical workers seem more spread out than they actually are.
For skewed distributions, consider median absolute deviation or interquartile range instead.
Standard deviation also breaks down with categorical data. It only works with numbers.
Getting Started: Your First Calculation
Grab a dataset with 10-20 numbers. Calculate the mean. Subtract it from each value. Square the results. Sum them. Divide by (n-1). Take the square root.
Do this manually once. You'll understand what the formula actually does instead of just punching numbers into a calculator. That understanding matters when something looks wrong with your results.