σ = 5, Y = 2X + 3
|2| × 5
10.
If every value is replaced by , the standard deviation becomes . Adding shifts the data but does not change its spread; multiplying by scales the spread by .
This page is easier if you are comfortable with:
The mean becomes , so each deviation from the mean becomes ; the shift cancels. Squaring and averaging gives variance , and the square root gives . See mean, variance and standard deviation; practice with transformed data is in coding of data.
A negative flips the data but the standard deviation stays positive, hence the absolute value. For temperatures, , so a standard deviation of 4 °C is °F. The data set 2, 4, 4, 4, 5, 5, 7, 9 has standard deviation 2, so has standard deviation 6.
The same rule for the variance, , is used with the standardising of a normal variable and with sums of independent random variables. The weighted version is in weighted averages.
Multiplying data scales its spread, while adding a constant only moves it.
The factor 3 triples the spread, the minus sign has no effect, and the +2 has no effect.
These examples are worked by hand, step by step, so you can compare your own working.
The data 2, 4, 4, 4, 5, 5, 7, 9 has standard deviation 2. Find the standard deviation of .
For the same data find the standard deviation of .
Temperatures in °C have standard deviation 4. Find the standard deviation in °F, where .
A few situations come up again and again. Knowing them saves time and helps you spot answers that cannot be right.
|2| × 5
10.
|−3| × 5
15.
a²σ²
100.
σ unchanged
5.
If Y = aX + b then σ_Y = |a|σ_X and Var(Y) = a²Var(X). Adding b shifts the data without changing spread.
σ_X = 5.
σ_X = 5.
σ² = 25, a = 2.
Y = X + 7.
σ + b ✗
unchanged ✓
Shift.
−15 ✗
15 ✓
Absolute value.
a σ² ✗
a²σ² ✓
Square.
unchanged ✗
ȳ = a x̄ + b ✓
Different.
Try each one on paper, then open the answer. Use the solver above to see the full working.
12
12
36
2.5
4
9
Unlimited fresh questions with instant marking. Choose a level, work it out on paper, then type your answer.
Solve: …
σ_Y = |a|σ_X.
No.
It is multiplied by a².
ȳ = a x̄ + b.
weighted average.
More in Finance and actuarial maths and the formula sheets.