Combining Normal Variables Explained with Worked Examples

If and are independent, then .

Write 2x or 2*x to multiply, ^ for powers, and ; between simultaneous equations. You can also type factor, expand, derivative of, integrate … from a to b, limit … as x->0 or 15% of 80.

Try an example

Before you start

This page is easier if you are comfortable with:

What Combining normal variables means

The mean and variance follow from the rules for linear transformations and sums of independent random variables. The special fact is that a linear combination of independent normal variables is itself exactly normal. The shape is that of the normal density, and probabilities come from standardising.

Example: and . Then , (the variances add), and , since . The probability that is .

Applications: total weight of several items, the mean of a sample (variance , used in confidence intervals), and differences between two groups in hypothesis tests. The moment generating function proof is in the mgf of the normal. Normal probabilities themselves are computed with the error function.

What is it used for?

A sum or difference of independent normal variables is again normal, with the variances added.

How to use combining normal variables

  1. Compute the new mean .
  2. Compute the new variance .
  3. State that the result is normal with these parameters.
  4. Standardise to find probabilities.

Graph

X − Y ~ N(5, 13): P(X − Y > 0) = 0.9172mean 5zero line-8-6-4-202468101214161800.020.040.060.080.10.12X − Y ~ N(5, 13): P(X − Y > 0) = 0.9172xydensity of X − YGraph with x from -8 to 18 and y from 0 to 0.13. Shows the curve density of X − Y; point mean 5 at (5, 0.11064); point zero line at (0, 0.0943).

Most of the area lies to the right of 0, so X is usually bigger than Y.

Worked examples

These examples are worked by hand, step by step, so you can compare your own working.

Example 1: sum

If and are independent, find the distribution of .

Worked example
Answer
N(15, 13)N(15,\ 13)
  1. Mean
  2. Variance

Example 2: 2X + 3Y

For the same variables find the distribution of .

Worked example
Answer
N(35, 97)N(35,\ 97)
  1. Mean
  2. Variance

Example 3: probability X > Y

For the same variables find .

Worked example
Answer
0.91720.9172
  1. X − Y
  2. Standardise
  3. Probability

Special cases

A few situations come up again and again. Knowing them saves time and helps you spot answers that cannot be right.

X ~ N(10, 4), Y ~ N(5, 9)

X + Y mean

15.

same

X + Y variance

13.

same

X − Y mean

5.

same

2X + 3Y variance

97.

Word problems

For independent normals, aX + bY ~ N(aμ_X + bμ_Y, a²σ_X² + b²σ_Y²).

Mean of X + Y

10 + 5.

  1. 15
  2. Check: ✓15

Variance

4 + 9.

  1. 13
  2. Check: ✓13

X − Y mean Higher

10 − 5.

  1. 5
  2. Check: ✓5

2X + 3Y variance Higher

4×4 + 9×9.

  1. 16 + 81
  2. Check: ✓97

Common mistakes

Var(X − Y) = 4 − 9

subtract ✗

add ✓

Variances add.

Adding SDs

2 + 3 ✗

add variances ✓

SD = √13.

Forgetting a²

2 × 4 ✗

4 × 4 ✓

Square.

Dependent variables

any ✗

independent only ✓

Condition.

Exam tips

  1. Means combine linearly.
  2. Variances: a²σ² + b²σ².
  3. Differences add variances.
  4. Result is normal.
  5. Standardise to find probabilities.

Practice questions

Try each one on paper, then open the answer. Use the solver above to see the full working.

1. Mean of 3X + Y: μ = 2 and 4 Foundation

10

2. Variance of 3X + Y: 1 and 5 Foundation

14

3. Variance of X − Y: 6 and 3 Foundation

9

4. SD of X + Y: variances 9 and 16 Higher

5

5. Mean of X − 2Y: 10 and 3 Higher

4

6. Variance of X − 2Y: 2 and 1 Higher

6

Practice generator

Unlimited fresh questions with instant marking. Choose a level, work it out on paper, then type your answer.

Solve: …

Key terms

Normal distribution
N(μ, σ²).
Independent
No influence.
Linear combination
aX + bY.
Variance
σ².
Standard deviation
√variance.
Combined variable
The result.

Frequently asked questions

What is the distribution of X + Y?

Normal with summed means and variances.

What about X − Y?

Mean difference, variances add.

What about aX + bY?

Mean aμ_X + bμ_Y, variance a²σ_X² + b²σ_Y².

Do SDs add?

No.

Which page covers sums?

sum of independent variables.

Which page covers standardising?

standardising a normal.

More in Advanced statistics and stochastic processes and the formula sheets.