Course contentsShow
← Mathematics
Lesson 2912 of 3,12157. Common DistributionsFree lesson

Linear Combinations of Normal Variables

How sums and differences of independent normal variables remain normally distributed.

Linear Combinations of Normal Variables

What you'll learn: How to work with sums and differences of independent normal random variables—and why they stay normal.

The Core Idea

One of the most elegant properties of the normal distribution is this: when you add or subtract independent normal random variables, the result is still normally distributed. You don't get some strange new shape—you get another normal curve.

If X ~ N(μ₁, σ₁²) and Y ~ N(μ₂, σ₂²) are independent, then any linear combination aX + bY (where a and b are constants) is also normal:

aX + bY ~ N(aμ₁ + bμ₂, a²σ₁² + b²σ₂²)

Notice how this works:

  • Means add linearly: The new mean is just a times the first mean plus b times the second mean
  • Variances scale with squares: The new variance is a² times the first variance plus b² times the second variance (because variance scales with the square of constants)

Why This Matters

This property makes the normal distribution incredibly tractable. For example:

  • The difference X - Y is just a special case where a = 1 and b = -1
  • The sum X + Y uses a = 1 and b = 1
  • You can combine multiple independent normals and still stay in the normal family

Example

If test scores X ~ N(75, 100) and Y ~ N(80, 64) are independent, then the difference in scores X - Y ~ N(75 - 80, 100 + 64) = N(-5, 164). You can now standardize and find probabilities just like any normal variable!

Key Takeaway: Linear combinations of independent normal variables remain normally distributed, with means that combine linearly and variances that add (weighted by squared coefficients).