All subjects · Mathematics · WST02 Statistics 2

The Poisson approximation to the binomial

Edexcel IAL Mathematics · WST02 Statistics 2

When n is large and p is small, binomial probabilities are awkward to calculate. B(n, p) is then well approximated by Po(np), which has the same mean.

Practise this in the app: instant marking and a fix for every mistake. Free, no email needed to start.

Practise this lesson

The approximation

If X ~ B(n, p) with n large and p small, then X can be approximated by Po(np).

The specification gives no fixed cut-off; a rough guide is n > 50 and p < 0.2, but the mark scheme wording is simply 'n is large and p is small'. When justifying the approximation you need both conditions; examiners report that giving only one loses the mark. 'The mean is close to the variance' is not accepted as a justification.

Why it works

B(n, p) has mean np and variance np(1 - p). When p is small, 1 - p is close to 1, so the variance is close to np: the mean and variance are nearly equal, as for a Poisson distribution with λ = np.

If p is close to 1

Count failures. If 97% of 150 components work, the number that fail is B(150, 0.03), which is approximately Po(4.5).

If a question says 'use a suitable approximation', an exact binomial answer usually loses marks, so use the Poisson distribution as asked.

Worked example

2% of items from a machine are faulty. In a sample of 200, use a suitable approximation to find the probability that at most 3 are faulty.

  1. X ~ B(200, 0.02); n is large and p is small, so X ≈ Po(4).
  2. P(X ≤ 3) from the Po(4) table

Answer: 0.4335 (the exact binomial value is 0.4315)

Key idea: B(n, p) ≈ Po(np) when n is large and p is small (rough guide: n > 50, p < 0.2). Give both conditions. Count failures if p is near 1.

Check yourself

  1. X ~ B(200, 0.02). Use a Poisson approximation to find P(X ≤ 3). Give your answer to 4 decimal places.
    Show answer

    0.4335. λ = 200 × 0.02 = 4. P(X ≤ 3) from the Po(4) table = 0.4335.

  2. X ~ B(400, 0.005). State the value of λ for a Poisson approximation.
    Show answer

    2. λ = np = 400 × 0.005 = 2.

  3. X ~ B(300, 0.01). Use a Poisson approximation to find P(X = 5). Give your answer to 4 decimal places.
    Show answer

    0.1008. Po(3): e-3 × 35 / 5! = 0.1008.

  4. 97% of components work. In a box of 150, use a suitable approximation to find the probability that at least 148 work. Give your answer to 4 decimal places.
    Show answer

    0.1736. Failures F ~ B(150, 0.03) ≈ Po(4.5). At least 148 work means F ≤ 2: P(F ≤ 2) = 0.1736.

  5. X ~ B(120, 0.025). Use a Poisson approximation to find P(X > 4). Give your answer to 4 decimal places.
    Show answer

    0.1847. Po(3): 1 - P(X ≤ 4) = 1 - 0.8153 = 0.1847.

  6. Which binomial distribution is best approximated by a Poisson distribution?
    • B(20, 0.4)
    • B(10, 0.05)
    • B(100, 0.5)
    • B(500, 0.004)
    Show answer

    B(500, 0.004). n is large and p is small.

  7. Which justification of a Poisson approximation to B(200, 0.02) earns the mark?
    • The mean is close to the variance
    • n is large and p is small
    • n is large
    • p is less than 0.5
    Show answer

    n is large and p is small. Mark schemes require both conditions, n large and p small.

Practise with instant feedback

Sources

Last updated 8 November 2026. Spotted a mistake? Tell us.