Skip to topic
    ← Back to course topics

    Statistical distributions (AS Unit 2: Applied Mathematics A) — WJEC A-Level Mathematics

    Statistical distributions (AS Unit 2: Applied Mathematics A) explained

    Statistical distributions (AS Unit 2: Applied Mathematics A) covers 4 specification points, including Understand and use simple, discrete… and Understand and use, • the binomial….

    Read the full explanation

    Open a point below for its explanation and revision guidance.

    Understand and use simple, discrete probability distributions.

    A discrete random variable X takes countable numerical outcomes with specified probabilities, defined via a table or formula P(X = x). Two foundational axioms must be satisfied: 0 ≤ P(X = x) ≤ 1 for every outcome x, and Σ P(X = x) = 1 across the support. In problems, distributions are often given in terms of an unknown constant k (e.g. P(X = x) = kx for x = 1, 2, 3, 4). Candidates sum the algebraic expressions over all possible values of x, equate the total to 1, solve for k, and evaluate probabilities for composite events such as P(X > 2) or P(1 ≤ X < 4).

    Understand and use, • the binomial distribution, as a model • the Poisson distribution, as a model • the discrete uniform distribution, as a model (Calculation of mean and variance of discrete random variables is excluded.)

    Candidates must understand the operational conditions required to model real phenomena with three discrete distributions. The binomial model X ~ B(n, p) applies when there is a fixed number of trials n, two mutually exclusive outcomes (success/failure), a constant probability of success p, and independent trials. The Poisson model X ~ Po(λ) models event counts in a fixed interval of space or time, assuming events occur singly, independently, and at a constant average rate λ. The discrete uniform distribution models n equally likely outcomes, each with probability 1/n, such as rolling an unbiased die.

    Calculate probabilities using • the binomial distribution. • the Poisson distribution. • the discrete uniform distribution.

    Discrete probability models are evaluated using formulae or calculator distribution functions. For X ~ B(n, p), P(X = r) = ⁿC_r p^r (1 − p)ⁿ⁻ʳ for r = 0, 1, ..., n, with mean np. For X ~ Po(λ), P(X = r) = (e^(−λ) λ^r)/r! for r = 0, 1, 2, ..., with mean λ. For a discrete uniform distribution on n equally likely outcomes, P(X = r) = 1/n. Cumulative probabilities come from Binomial CD and Poisson CD calculator modes. Rewrite P(X ≥ k) = 1 − P(X ≤ k − 1), P(X < k) = P(X ≤ k − 1), and P(a ≤ X ≤ b) = P(X ≤ b) − P(X ≤ a − 1). For example, if X ~ Po(3) then P(X ≥ 5) = 1 − P(X ≤ 4) ≈ 0.1847.

    Select an appropriate probability distribution for a context, with appropriate reasoning, including recognising when the binomial, Poisson or discrete uniform model may not be appropriate.

    Selecting an appropriate probability model requires comparing physical problem traits against distribution assumptions. The binomial model fits when trials are fixed and dichotomous, but fails if sampling without replacement causes p to vary. The Poisson model suits counts of rare events occurring in continuous time or space, but fails if events occur in pairs or clusters (violating the 'singly' condition) or if events influence one another. The discrete uniform model is valid when outcomes are symmetrical and unbiased, but invalid if some outcomes are favoured. Candidates critique model suitability and justify alternatives.

    Your focus

    1. Represent and interpret discrete probability distributions using tables and formulas.
    2. Determine unknown parameters in discrete distributions using the condition that total probability equals 1.
    3. Calculate probabilities for compound events by summing individual probability mass terms.
    Show all 13 objectives
    1. State and verify the four assumptions required to model a scenario with a binomial distribution.
    2. Explain the conditions necessary for a Poisson process: constant average rate, independence, and events occurring singly.
    3. Identify scenarios where equally likely discrete outcomes justify a discrete uniform distribution.
    4. Compute exact and cumulative probabilities for binomial distributions using formulae and calculator functions.
    5. Calculate Poisson probabilities, adjusting the rate parameter λ proportionally for different intervals.
    6. Convert discrete inequality ranges into cumulative expressions suitable for calculator inputs.
    7. Recognise and use the discrete uniform distribution with probability 1/n for each of n outcomes.
    8. Select the appropriate probability distribution model for a given scenario with stated parameters.
    9. Justify distribution choice by matching physical context conditions to mathematical axioms.
    10. Critique and reject inappropriate probability models by identifying violated theoretical assumptions.

    Statistical distributions (AS Unit 2: Applied Mathematics A) exam tips

    Marking Points
    • setting up the total probability equation Σ P(X = x) = 1 across all outcomes
    • solving the linear equation to find the exact value of the unknown parameter k
    • evaluating the probability of a compound event by summing relevant individual probabilities
    • stating the conditions for a binomial model: fixed n, independent trials, constant p, two outcomes
    • stating the conditions for a Poisson model: constant rate, independent occurrences, events occurring singly
    • identifying when a discrete uniform model applies due to equally likely outcomes
    • State the distribution and its parameters, for example X ~ B(20, 0.3) or X ~ Po(4), before calculating.
    • Rewrite an inequality in cumulative form, such as P(X ≥ 4) = 1 − P(X ≤ 3) or P(2 ≤ X ≤ 6) = P(X ≤ 6) − P(X ≤ 1).
    • Evaluate the probability correctly using the formula or calculator distribution functions, giving the answer to the required accuracy (often 3 significant figures).
    • Adjust the Poisson parameter λ proportionally when the time, length, area or volume interval changes, for example λ = 2 per hour becomes λ = 0.5 for a 15-minute interval.
    • Interpret the calculated probability in context, for example stating that approximately 18.5% of intervals of this length contain at least five events.
    • selecting the correct distribution (binomial, Poisson, or discrete uniform) with parameter values
    • justifying the choice by linking contextual conditions directly to theoretical assumptions
    • explaining why an alternative distribution is invalid due to a specific violated assumption
    Examiner Tips
    • 💡Show the full sum of probabilities equal to 1 clearly before solving for the unknown constant.
    • 💡List the discrete integer values satisfying an inequality before summing their respective probabilities.
    • 💡Memorise the exact conditions for binomial (fixed n, independent, constant p) and Poisson (singly, constant rate, independent).
    • 💡State the distribution and its parameters explicitly, e.g. X ~ B(20, 0.4) or X ~ Po(3.5).
    • 💡Write the cumulative expression, such as 1 − P(X ≤ 3), before using the calculator, so the method is visible and errors in the boundary value are easier to spot.
    • 💡Check whether the question gives a rate for a different interval from the one required, and rescale λ first; then use the Poisson CD function with the rescaled parameter.
    • 💡Always quote context when justifying distribution choice (e.g. 'flaws occur independently at a constant rate').
    • 💡To critique a model, identify a specific violated assumption such as non-constant probability or dependence.
    Common Mistakes
    • omitting outcomes when setting the sum of probabilities equal to 1
    • misinterpreting discrete inequalities, such as including x = 2 when evaluating P(X > 2)
    • applying a binomial model when sampling without replacement from a small population causes p to vary
    • using a Poisson distribution when events cluster together rather than occurring singly and independently
    • Calculating P(X ≥ k) as 1 − P(X ≤ k) instead of 1 − P(X ≤ k − 1); the correction is to subtract the probability of k itself as well, since the complement of X ≥ k is X ≤ k − 1.
    • Failing to scale the Poisson parameter λ when the interval changes; the correction is to multiply or divide λ by the same factor as the interval, since the mean number of events is proportional to interval size.
    • Using the binomial formula with r outside 0 ≤ r ≤ n, or treating a discrete uniform distribution as continuous; the correction is to check the support of the distribution and remember that each of the n outcomes has probability exactly 1/n.
    • selecting a binomial distribution when the total number of trials n is not fixed in advance
    • proposing a Poisson model when events cluster together (such as traffic arriving in convoys)