Expectation and Variance in Common Distributions
You'll learn: How to quickly find the mean and variance of binomial, geometric, and Poisson random variables using distribution-specific formulas.
The Core Idea
Rather than grinding through integrals or summations every time, each common distribution has closed-form formulas for expectation and variance. These formulas arise from the structure of each distribution and save enormous computational effort.
Binomial Distribution
For X ~ Binomial(n, p) (number of successes in n independent trials with success probability p):
- E[X] = np
- Var(X) = np(1 - p)
Intuition: If you flip a fair coin 100 times, you expect 50 heads on average. The variance accounts for spread around that mean.
Geometric Distribution
For X ~ Geometric(p) (number of trials until first success):
- E[X] = 1/p
- Var(X) = (1 - p)/p²
Intuition: If success probability is 0.2, you expect to wait 5 trials on average. Lower p means longer waits and more variability.
Poisson Distribution
For X ~ Poisson(λ) (number of events in a fixed interval, where λ is the rate):
- E[X] = λ
- Var(X) = λ
Remarkable property: Mean equals variance! The rate parameter λ completely determines both center and spread.
Why This Matters
These formulas let you instantly characterize a random variable without tedious calculations. For example, knowing that a call center receives calls at rate λ = 12 per hour (Poisson) immediately tells you both the average number and variance are 12.
Key Takeaway: Binomial, geometric, and Poisson distributions each have simple formulas for E[X] and Var(X) derived from their parameters—memorize these to efficiently analyze real-world random processes.