4.4

4.4 Means and Variances of Random Variables

  • We discover how means and variances can be calculated for populations described by discrete probability distributions.
  • Rules are given for calculating means and variances of simple functions of random variables.

Mean of a Discrete Random Variable

  • The usual symbol for the mean of a sample is x-bar:
  • The common symbol for the mean of a probability distribution is the Greek letter mu: μ.
  • We often call the mean of a random variable X the expected value of X and write it as E(X).

Definition and Calculation of Mean

  • Suppose the discrete random variable X has a distribution given by:
    • Value of X: x₁, x₂, …, xₖ
    • Probability: p₁, p₂, …, pₖ
    • The mean of X is calculated as:

      μ = x₁p₁ + x₂p₂ + … + xₖpₖ = extstyle rac{ extstyle extsum (x imes p)}{ extstyle extsum (p)}

Example: Mean Outcome of a Single Roll of a Die

  • Find the mean outcome of a single roll of a die:

Calculation

  • Each outcome has a probability of $ rac{1}{6}$
  • Outcomes: 1, 2, 3, 4, 5, 6
  • Therefore, the mean is calculated as:

    μ_X = rac{1}{6}(1) + rac{1}{6}(2) + rac{1}{6}(3) + rac{1}{6}(4) + rac{1}{6}(5) + rac{1}{6}(6)
  • This simplifies to:

    μ_X = rac{21}{6} = 3.5

Variance of a Discrete Random Variable

  • The usual symbol for the variance of a sample is s².
  • The common symbol for the variance of a probability distribution uses the Greek letter sigma: σ².
  • The square root of the variance is the standard deviation σ.

Definition and Calculation of Variance

  • Suppose the discrete random variable X has a distribution given as:
    • Value of X: x₁, x₂, …, xₖ
    • Probability: p₁, p₂, …, pₖ
    • The Variance of X is calculated as:

      extstyleσ² = extstyle extsum (pi (xi - μ)²)

Example: Variance of the Outcome X of a Single Roll of a Die

  • Find the variance of the outcome X of a single roll of a die:

Calculation

  • Each outcome has a probability of $ rac{1}{6}$
  • Outcomes: 1, 2, 3, 4, 5, 6
  • The mean has already been calculated as 3.5.
  • Therefore, we calculate the variance:

    σ²_X = rac{1}{6} (1 - 3.5)² + rac{1}{6} (2 - 3.5)² + rac{1}{6} (3 - 3.5)² + rac{1}{6} (4 - 3.5)² + rac{1}{6} (5 - 3.5)² + rac{1}{6} (6 - 3.5)²
  • This simplifies to:

    σ²_X = rac{1}{6}(6.25 + 2.25 + 0.25 + 0.25 + 2.25 + 6.25) = rac{17.5}{6} ext{ or } 2.9167

Law of Large Numbers

  • Draw independent observations at random from any population.
  • Decide how accurately you would like to estimate the population mean μ.
  • As the sample size n increases, the sample mean eventually approaches the population mean μ as close as you specify and then stays that close.

Example: Heights of Young Women

  • Example data illustrated:
    • Mean heights:
    • Heights at a certain age: 66.0, 65.5, 65.0, 64.5, 64.0, 63.5, 63.0
  • Mean of first n:
    • Obtained for increasing sample sizes: n = 0, 5, 10, 100, 1000, 10,000.

Rules for Means

  1. If X is a random variable and a and b are constant real numbers:

    μ{a + bX} = a + bμX
  2. If X and Y are random variables:

    μ{X + Y} = μX + μ_Y

Rules for Variances

  1. If X is a random variable and a and b are constant real numbers:

    σ²{a + bX} = b²σ²X

  2. If X and Y are independent random variables:

    • The variances combine as follows:

      σ²{X + Y} = σ²X + σ²Y σ²{X - Y} = σ²X + σ²Y
  3. If X and Y are random variables with correlation coefficient ρ:

    • Variances with correlation included:

      σ²{X + Y} = σ²X + σ²Y + 2ρσXσY σ²{X - Y} = σ²X + σ²Y - 2ρσXσY