The expected value E(X) = Σ x · P(X = x) is the long-run average value of a random variable over many repetitions of the experiment. It is a weighted average of all possible values, where each weight is the corresponding probability. E(X) need not be a value the variable can actually take — for a fair die, E(X) = 3.5. Key properties: E(aX + b) = aE(X) + b, and for independent variables, E(X + Y) = E(X) + E(Y).
Games of chance (lotteries, casino games) make expected value immediately meaningful. Have students compute expected payoffs to determine whether a game is fair. Then connect to the long-run frequency interpretation with simulations.
Expected value is the foundational concept linking probability to real-world decision-making. Informally, it answers: if you repeated this random experiment a very large number of times, what would the average outcome be? You compute it by multiplying each possible outcome by its probability and summing those products: E(X) = Σ x · P(X = x). Because you already know sigma notation and random variables, you have exactly the tools needed to read and apply this formula.
The "weighted average" framing is key to building intuition. Suppose a lottery ticket costs $2 and pays $100 with probability 0.01 and $0 otherwise. The simple average of possible payouts is ($100 + $0) / 2 = $50, which wildly overstates the ticket's worth. The expected value is $100 × 0.01 + $0 × 0.99 = $1.00 — below the $2 purchase price, so the game is unfair to the buyer. Expected value is the right tool precisely because it weights outcomes by how often they occur.
A critical subtlety: the expected value does not need to be an achievable outcome. A fair die has E(X) = 3.5, but you will never roll a 3.5. E(X) is not a prediction about any single trial; it describes the long-run behavior across many trials. If you rolled the die 6,000 times, the average of all rolls would be very close to 3.5. This long-run-average interpretation is the correct way to understand expected value.
Two properties are especially useful. First, linearity: E(aX + b) = aE(X) + b. This means if you double all payouts and add a $5 bonus, expected value doubles and gains $5. Second, additivity: E(X + Y) = E(X) + E(Y) for any two random variables, even dependent ones. This is surprisingly powerful — it lets you compute the expected total of complex combinations without worrying about how the individual variables relate to each other.
Expected value is a building block for variance, distributions, and statistical inference. When you encounter the binomial distribution or sampling distributions next, you will see expected value used to describe the center of these distributions. In economics and decision theory, it is the foundation of rational choice under uncertainty.