4.3: Binomial Distribution Study Guide

Characteristics of a Binomial Experiment and Distribution

  • When a random variable follows a specific underlying structure, standard probability calculations and statistical measures such as the mean and standard deviation simplify significantly.

  • The binomial distribution is a continuous discrete probability distribution function representing repeated binary events.

  • A binomial experiment is defined by three strict criteria:

    • Fixed number of trials: The experiment consists of a fixed number of repeated trials, denoted by the variable nn.

    • Two possible outcomes: Each individual trial yields exactly one of two possible outcomes, categorized as "success" or "failure".

    • The probability of a success is represented by p=P(Success)p = P(\text{Success}).

    • The probability of a failure is represented by q=P(Failure)q = P(\text{Failure}).

    • Because these outcomes are complementary, the probabilities must sum to one: p+q=1p + q = 1, or equivalently q=1−pq = 1 - p.

    • Independence of trials: All nn trials are strictly independent. The outcome of any single trial provides no information to alter or predict the outcome of any other trial.

  • Definition of the Random Variable:

    • If a variable XX is defined as "the number of successes after nn trials," then XX represents a binomial probability distribution.

    • This relationship is written in formal statistical notation as X∼B(n,p)X \sim B(n, p), read as "XX is a random variable following a binomial distribution with nn trials and probability of success pp".

  • Bernoulli Trial:

    • A single trial (n=1n = 1) under binomial conditions is formally referred to as a Bernoulli Trial.

  • Real-World Example (Travis Kelce Catch Percentage):

    • As of the conclusion of the 2024 season, Travis Kelce holds a catch percentage per game of 41%41\% (p=0.41p = 0.41).

    • Assuming 1212 catch attempts in a given game (n=12n = 12), each attempt can be treated as an independent trial.

    • Defining XX as the "number of successful catches in a game" allows the random variable to be modeled as X∼B(12,0.41)X \sim B(12, 0.41).

Formulas for Binomial Mean and Standard Deviation

  • For any random variable following a binomial distribution X∼B(n,p)X \sim B(n, p), the central formulas for mean (expected value) and standard deviation simplify from general discrete random variable formulas:

    • Mean Formula:     μ=np\mu = np

    • Standard Deviation Formula:     σ=npq=np(1−p)\sigma = \sqrt{npq} = \sqrt{np(1 - p)}

  • Example 1 (Coin Tossing):

    • Scenario: Tossing a fair coin 44 times (n=4n = 4) and counting the total number of heads (p=0.5p = 0.5).

    • Random Variable Model: X∼B(4,0.5)X \sim B(4, 0.5).

    • Mean Calculation:     μ=np=4×0.5=2\mu = np = 4 \times 0.5 = 2

    • Standard Deviation Calculation:     σ=np(1−p)=4×0.5×(1−0.5)=4×0.5×0.5=1=1\sigma = \sqrt{np(1 - p)} = \sqrt{4 \times 0.5 \times (1 - 0.5)} = \sqrt{4 \times 0.5 \times 0.5} = \sqrt{1} = 1

  • Example 2 (Die Rolling):

    • Scenario: Rolling a fair standard six-sided die 99 times (n=9n = 9) and counting the total number of 66s rolled (p=16p = \frac{1}{6}).

    • Random Variable Model: X∼B(9,16)X \sim B\left(9, \frac{1}{6}\right).

    • Mean Calculation:     μ=np=9×16=96=1.5\mu = np = 9 \times \frac{1}{6} = \frac{9}{6} = 1.5

    • Standard Deviation Calculation:     σ=np(1−p)=9×16×(1−16)=9×16×56=4536=1.25≈1.118\sigma = \sqrt{np(1 - p)} = \sqrt{9 \times \frac{1}{6} \times \left(1 - \frac{1}{6}\right)} = \sqrt{9 \times \frac{1}{6} \times \frac{5}{6}} = \sqrt{\frac{45}{36}} = \sqrt{1.25} \approx 1.118

Calculating Binomial Probabilities

  • Domain of the Random Variable:

    • For X∼B(n,p)X \sim B(n, p), the variable xx represents the count of successes and can equal any integer from 00 through nn (x∈{0,1,2,…,n}x \in \{0, 1, 2, \dots, n\}).

  • Probability Mass Function (Binomial Formula):

    • The probability of observing exactly kk successes out of nn trials is calculated using the formula:     P(x=k)=(nk)pk(1−p)n−kP(x = k) = \binom{n}{k} p^k (1 - p)^{n - k}

    • Combinatorial Notation:

    • The expression (\binom{n}{k}) represents the combinations of nn items taken kk at a time, evaluated as:       (nk)=n!k!(n−k)!\binom{n}{k} = \frac{n!}{k!(n - k)!}

Histogram Representation of Binomial Distributions

  • Area Principle of Probability Histograms:

    • In a discrete probability histogram, the probability of obtaining a specific outcome or set of outcomes corresponds directly to the visual area of the representative bar(s).

  • Visual Representation of B(10,0.3)B(10, 0.3), showing exact probabilities for each outcome x∈{0,1,…,10}x \in \{0, 1, \dots, 10\}.

Histogram of Binomial Distribution B(10, 0.3)
  • Discrete Probability Data for X∼B(10,0.3)X \sim B(10, 0.3), taken directly from the distribution histogram:

    • P(x=0)=0.02825P(x = 0) = 0.02825

    • P(x=1)=0.12106P(x = 1) = 0.12106

    • P(x=2)=0.23347P(x = 2) = 0.23347

    • P(x=3)=0.26683P(x = 3) = 0.26683

    • P(x=4)=0.20012P(x = 4) = 0.20012

    • P(x=5)=0.10292P(x = 5) = 0.10292

    • P(x=6)=0.03676P(x = 6) = 0.03676

    • P(x=7)=0.00900P(x = 7) = 0.00900

    • P(x=8)=0.00145P(x = 8) = 0.00145

    • P(x=9)=0.00014P(x = 9) = 0.00014

    • P(x=10)=0.00001P(x = 10) = 0.00001

  • Example Interval Calculation:

    • Problem Statement: Using the histogram data for X∼B(10,0.3)X \sim B(10, 0.3), calculate the probability P(3≤x≤7)P(3 \le x \le 7).

    • Solution Procedure: Sum the discrete probability rectangle areas for all integer values in the range [3,7][3, 7]:     P(3≤x≤7)=P(x=3)+P(x=4)+P(x=5)+P(x=6)+P(x=7)P(3 \le x \le 7) = P(x = 3) + P(x = 4) + P(x = 5) + P(x = 6) + P(x = 7)

    • Numerical Calculation:     P(3≤x≤7)=0.26683+0.20012+0.10292+0.03676+0.00900=0.61563P(3 \le x \le 7) = 0.26683 + 0.20012 + 0.10292 + 0.03676 + 0.00900 = 0.61563

Calculating Binomial Probabilities Using Spreadsheet Software

  • Spreadsheet Function Overview:

    • Software programs such as Google Sheets feature dedicated functions to evaluate individual and cumulative binomial probabilities.

  • Function Syntax:

    • =BINOMDIST(k, n, p, cumulative)

  • Evaluating Exact Individual Probability P(x=k)P(x = k):

    • Setting the cumulative argument to FALSE returns the probability density function value at x=kx = k:     =BINOMDIST(k, n, p, FALSE) computes P(x=k)P(x = k) for X∼B(n,p)X \sim B(n, p).

  • Evaluating Cumulative Probability P(x≤k)P(x \le k):

    • Setting the cumulative argument to TRUE computes the total probability of obtaining kk or fewer successes:     =BINOMDIST(k, n, p, TRUE) computes P(x≤k)P(x \le k) for X∼B(n,p)X \sim B(n, p).

  • Calculating Range Probabilities P(a≤x≤b)P(a \le x \le b) with Cumulative Functions:

    • The probability of a variable falling within a inclusive range a≤x≤ba \le x \le b is obtained using cumulative upper and lower boundaries:     P(a≤x≤b)=P(x≤b)−P(x≤a−1)P(a \le x \le b) = P(x \le b) - P(x \le a - 1)

    • For the interval P(3≤x≤7)P(3 \le x \le 7) where X∼B(10,0.3)X \sim B(10, 0.3), set a=3a = 3 and b=7b = 7:     P(3≤x≤7)=P(x≤7)−P(x≤2)P(3 \le x \le 7) = P(x \le 7) - P(x \le 2)

    • Equivalent Spreadsheet Formula Expression:     =BINOMDIST(7, 10, 0.3, TRUE) - BINOMDIST(2, 10, 0.3, TRUE)