AP Statistics · Unit 2 · Topic 2.10

The Binomial Distribution Study Lab

A binomial random variable counts the successes in a fixed number of independent trials that each have the same chance of success. Check the conditions, set n and p, choose an event, and see the shaded bars, the formula, and the calculator command that gives the same answer.

1. Set up a binomial model

Pick a situation. Check B-I-N-S first: if any condition fails, the binomial model does not apply.

P(X = k) = ₙCk · pk · (1 − p)n − k μ = np σ = √(np(1 − p))
Situations

Conditions

    and)

    Binomial distribution

    Probability of the event
    Mean μ = np
    SD σ = √(np(1 − p))
    Shape

    By the formula

    On the calculator

    2. Key ideas

    B

    Binary outcomes

    Each trial ends in one of two outcomes, called "success" and "failure." Success just means the outcome you are counting, even if it is something bad like a defect.

    I

    Independent trials

    Knowing the result of one trial does not change the probabilities for another. When sampling without replacement, use the 10% condition: n ≤ 10% of the population lets you treat trials as roughly independent.

    N

    Number of trials fixed

    You decide n in advance, like 10 free throws or 20 customers. If you keep going until a success, the count is not binomial.

    S

    Same probability

    The probability of success p is the same on every trial. A shooter who gets tired, or a deck that changes as cards are dealt, breaks this condition.

    Center and spread

    μ = np, σ = √(np(1 − p))

    The mean is the expected number of successes. The spread is largest when p = 0.5 and shrinks as p moves toward 0 or 1.

    Shape

    Skewed or symmetric?

    Small p gives a right-skewed distribution and large p a left-skewed one. When np ≥ 10 and n(1 − p) ≥ 10, the shape is approximately normal.

    3. Calculator commands

    binompdf gives one exact value; binomcdf gives "at most." Everything else is built from those two.

    EventCommandExample: n = 10, p = 0.3Answer
    Exactly k: P(X = 3)binompdf(n, p, k)binompdf(10, 0.3, 3)0.2668
    At most k: P(X ≤ 3)binomcdf(n, p, k)binomcdf(10, 0.3, 3)0.6496
    Fewer than k: P(X < 3)binomcdf(n, p, k − 1)binomcdf(10, 0.3, 2)0.3828
    At least k: P(X ≥ 3)1 − binomcdf(n, p, k − 1)1 − binomcdf(10, 0.3, 2)0.6172
    More than k: P(X > 3)1 − binomcdf(n, p, k)1 − binomcdf(10, 0.3, 3)0.3504
    Between: P(2 ≤ X ≤ 4)binomcdf(n, p, 4) − binomcdf(n, p, 1)0.8497 − 0.14930.7004

    4. On the FRQ

    How to earn the points

    • Define X and name the distribution with its parameters: "X = number of defective chips; X is binomial with n = 20 and p = 0.05."
    • Check the conditions in context, especially independence and the 10% condition when sampling without replacement.
    • Write the probability statement, then the work: "P(X ≥ 2) = 1 − P(X ≤ 1) = 1 − binomcdf(20, 0.05, 1) = 0.264." Label the calculator inputs if you use calculator syntax.
    • Interpret μ = np as the long-run average count: "Over many batches of 20, the average number of defective chips is 1."
    • Answer the question asked: if they ask whether a result is surprising, compare its probability to a small cutoff and explain.

    Common mistakes

    • Using binomcdf for "at least." binomcdf always means "at most," so P(X ≥ k) = 1 − binomcdf(n, p, k − 1).
    • Off-by-one errors with "more than" and "fewer than."
    • Calling a count binomial when the number of trials is not fixed, such as "flip until the first head."
    • Forgetting the 10% condition when drawing people or items without replacement.
    • Writing only "binomcdf(20, .05, 1)" with no labels. Readers need to know what n, p, and k are.

    5. Practice questions

    AP-style multiple choice. Pick an answer to see the explanation.

    0 / 0 correct

    6. Key terms

    The vocabulary for topic 2.10. Read the list, flip through flashcards, or quiz yourself. For every term in the unit, see the Unit 2 terminology guide.