Introduction to Expected Values

Expected Value: A Comprehensive Guide What is Expected Value? The expected value of a random variable is the long-run average outcome you would observe if you repeated a random experiment many times. It's denoted by $E[X]$ or sometimes by the Greek letter $\mu$. Think of expected value as the "center of mass" of a probability distribution—where outcomes tend to cluster when weighted by their probabilities. If you roll a fair die repeatedly and compute the average of your rolls, that average will eventually settle around the expected value of the die. An important insight: expected value is not required to be a possible outcome of the random variable itself. For example, the expected value of rolling a fair die is 3.5, yet you can never actually roll a 3.5. Expected Value for Discrete Random Variables For a discrete random variable—one that can take on a finite or countably infinite number of specific values—computing the expected value is straightforward. If your random variable $X$ can take values $x1, x2, \dots, xk$ with probabilities $p1, p2, \dots, pk$ respectively, then: $$E[X] = \sum{i=1}^{k} xi \, pi$$ In words: multiply each possible outcome by its probability, then add all these products together. Remember: the probabilities must satisfy $\sum{i=1}^{k} pi = 1$ (they sum to 1). Example: Rolling a Fair Die A fair six-sided die has outcomes 1, 2, 3, 4, 5, 6, each with probability $\frac{1}{6}$. The expected value is: $$E[X] = 1 \cdot \frac{1}{6} + 2 \cdot \frac{1}{6} + 3 \cdot \frac{1}{6} + 4 \cdot \frac{1}{6} + 5 \cdot \frac{1}{6} + 6 \cdot \frac{1}{6} = \frac{21}{6} = 3.5$$ Each outcome contributes equally to the average because each has equal probability. Expected Value for Continuous Random Variables For continuous random variables—which can take any value within an interval—expected value is computed using integration instead of summation. If $X$ is a continuous random variable with probability density function $f(x)$, then: $$E[X] = \int{-\infty}^{\infty} x \, f(x) \, dx$$ The probability density function must satisfy $\int{-\infty}^{\infty} f(x) \, dx = 1$, analogous to probabilities summing to 1 in the discrete case. The integral averages the outcomes weighted by their probability density. Just as with the discrete case, you're multiplying values by their probabilities (or probability densities) and summing the contributions. Key Properties of Expected Value Linearity of Expectation One of the most powerful properties is linearity of expectation. For any constants $a$ and $b$ and any random variables $X$ and $Y$: $$E[aX + bY] = a \, E[X] + b \, E[Y]$$ This property is remarkable because it holds regardless of whether $X$ and $Y$ are independent. This makes expected value incredibly useful: you can break complex expressions into simpler pieces, compute their expectations separately, and combine the results. Example: If $X$ has expected value 10 and $Y$ has expected value 5, then $E[2X + 3Y] = 2(10) + 3(5) = 35$. Non-negativity of Expectation If a random variable $X$ is always non-negative (i.e., $X \geq 0$ always), then its expected value must also be non-negative: $E[X] \geq 0$. This is intuitive: if you only have non-negative outcomes and you average them (weighted by probability), you cannot get a negative result. The Law of Large Numbers: Why Expected Value Matters The Law of Large Numbers explains why expected value is such a powerful concept. This theorem states that if you repeatedly draw independent samples from the same distribution, the average of those samples converges toward the expected value as the number of samples increases. In other words, if you have independent, identically distributed observations $X1, X2, X3, \ldots, Xn$ from a random variable with expected value $\mu$, then the sample average $$\bar{X}n = \frac{1}{n}(X1 + X2 + \cdots + Xn)$$ gets closer and closer to $\mu$ as $n$ grows large. This explains the intuitive interpretation of expected value as a "long-run average." This convergence is not just a theoretical nicety—it's the foundation for why we can use expected value as a reliable predictor of behavior over time, which makes it essential for practical applications in finance, insurance, and engineering. Why Expected Value Matters in Statistics and Probability Expected value is a cornerstone concept with wide-ranging applications: Foundation for variance: Variance, which measures the spread of a distribution, is itself defined using expected value: $\text{Var}(X) = E[(X - E[X])^2]$. You cannot understand variability without understanding expectation. Higher-order moments: Expected value extends to computing second moments $E[X^2]$, skewness, and other descriptors of a distribution's shape. Risk assessment: In finance and insurance, expected value helps quantify risk. Insurance premiums are priced based on the expected value of claims. Investment decisions depend on expected returns. Statistical estimation: When designing estimators (methods to guess unknown population parameters), expected value guides us toward unbiased estimators—those whose expected value equals the true parameter. Decision-making: Expected value provides a rational framework for comparing uncertain outcomes, which is essential in business, medicine, and policy decisions.