Applications: Sums of Normal and Binomial RVs
What you'll learn: How to use MGFs to prove that sums of normal random variables are normal and sums of binomial random variables are binomial.
The Core Idea
You've learned that the MGF of a sum of independent random variables equals the product of their individual MGFs, and that MGFs uniquely identify distributions. Now we can apply these powerful tools to answer questions about the distributions of sums.
Sums of Normal Random Variables
Suppose X₁ ~ N(μ₁, σ₁²) and X₂ ~ N(μ₂, σ₂²) are independent. What is the distribution of X₁ + X₂?
The MGF of a normal N(μ, σ²) is M(t) = exp(μt + σ²t²/2).
For the sum:
- M_{X₁+X₂}(t) = M_{X₁}(t) · M_{X₂}(t)
- = exp(μ₁t + σ₁²t²/2) · exp(μ₂t + σ₂²t²/2)
- = exp[(μ₁ + μ₂)t + (σ₁² + σ₂²)t²/2]
This is the MGF of N(μ₁ + μ₂, σ₁² + σ₂²)! So the sum of independent normals is normal, with means and variances adding.
Sums of Binomial Random Variables
Suppose X₁ ~ Binomial(n₁, p) and X₂ ~ Binomial(n₂, p) are independent (same success probability p).
The MGF of Binomial(n, p) is M(t) = (pe^t + 1 - p)^n.
For the sum:
- M_{X₁+X₂}(t) = (pe^t + 1 - p)^{n₁} · (pe^t + 1 - p)^{n₂}
- = (pe^t + 1 - p)^{n₁ + n₂}
This is the MGF of Binomial(n₁ + n₂, p)! The sum of independent binomials (with the same p) is binomial with total trials.
Key Takeaway: MGFs provide elegant proofs that sums of normals stay normal and sums of binomials stay binomial, with parameters combining naturally—a fact you can verify by uniqueness of MGFs.