Expectation and Variance of Binomial Distribution
You'll learn: How to derive that a binomial random variable X ~ Binomial(n, p) has expectation E[X] = np and variance Var(X) = np(1-p).
The Core Idea
A binomial random variable counts the number of successes in n independent Bernoulli trials, each with success probability p. Rather than computing expectation and variance directly from the PMF (which gets messy), we can use a clever trick: write X as the sum of n independent Bernoulli random variables.
The Derivation
Let X₁, X₂, ..., Xₙ be independent Bernoulli(p) random variables (each represents one trial). Then:
X = X₁ + X₂ + ... + Xₙ
From our earlier work with Bernoulli distributions, we know:
- E[Xᵢ] = p for each i
- Var(Xᵢ) = p(1-p) for each i
Finding the Expectation
Using linearity of expectation:
E[X] = E[X₁ + X₂ + ... + Xₙ] = E[X₁] + E[X₂] + ... + E[Xₙ] = p + p + ... + p = np
This makes intuitive sense: if you flip 10 coins with p = 0.5 each, you expect 5 heads on average.
Finding the Variance
Since the trials are independent, we can add variances:
Var(X) = Var(X₁) + Var(X₂) + ... + Var(Xₙ) = p(1-p) + p(1-p) + ... + p(1-p) = np(1-p)
Notice how variance depends on both n and the "uncertainty" term p(1-p), which is maximized when p = 0.5.
Key Takeaway: For X ~ Binomial(n, p), the expectation is E[X] = np (the average number of successes) and the variance is Var(X) = np(1-p), derived by viewing X as a sum of independent Bernoulli trials.