Scribe logoScribeNotes & practice
Sign inStart free
  1. Notes
  2. ›IB Mathematics: Applications and Interpretation
  3. ›4 Statistics and probability
  4. ›4.17 Poisson distribution

IB Mathematics: Applications and Interpretation · Topic 4 · Statistics and probability

4.17 Poisson distribution

Identify situations suited to a Poisson model, calculate Poisson probabilities, state its mean and variance, and interpret results in context.

  • 4 min read
  • 5 parts
  • 10 questions
  • Draft
  • HL only
Start a Quick 5 on this topic→Jump to the 10 questions
1/5The Poisson distribution counts random events in a fixed period
  1. 1The Poisson distribution counts random events in a fixed period
  2. 2A Poisson model needs random, independent events at a steady rate
  3. 3Poisson probabilities come from one formula or a calculator
  4. 4The mean and variance of a Poisson distribution are equal
  5. 5Probabilities must be interpreted in the context of the situation
  6. Check your recall
  7. Practice: 10 questions
1

Part 1 of 5: The Poisson distribution counts random events in a fixed period

A call centre receives calls at random through the morning. Over many hours the average stays steady at 6 calls per hour. The number of calls in one hour can be modelled by a Poisson distribution.

We write X∼Po(m)X\sim\mathrm{Po}(m)X∼Po(m). Here XXX is the number of events in one period, and mmm is the mean number of events per period. For the call centre, m=6m=6m=6 for one hour.

The possible values of XXX are the whole numbers 0,1,2,…0,1,2,\dots0,1,2,…, so the distribution is discrete.

Exam tip

Always state the period that mmm refers to. A count over one hour and a count over half an hour have different means.

Key term

Poisson distribution

A Poisson distribution is the discrete distribution Po(m)\mathrm{Po}(m)Po(m) for the number of random, independent events in a fixed period with mean mmm.

Part 1 done

2

Part 2 of 5: A Poisson model needs random, independent events at a steady rate

Not every count of events suits this model. Four conditions must hold.

  • Events occur one at a time, never in groups.
  • Events are independent: one event does not change the chance of another.
  • Events occur at a constant average rate.
  • The count is taken over a fixed period or region.

Faults along a cable fit well. Cars at a junction fit only if traffic is steady, because rush hour changes the rate.

Common mistake

Do not use a Poisson model for a fixed number of trials, each a success or a failure. That situation needs a binomial model.

Key term

constant average rate

A constant average rate means the mean number of events per unit of time or space does not change.

Part 2 done

Quick check

One question on the part you just read

Easy

Identify the situation that is most suitable for a Poisson model.
Show answer and explanation

Answer: A · Worked explanation

Faults occurring at random along a cable, at a steady rate, can be counted with no fixed number of trials. The other three describe a fixed number of trials with success or failure, which is not a Poisson situation.
3

Part 3 of 5: Poisson probabilities come from one formula or a calculator

With the conditions met, we can find probabilities. For X∼Po(m)X\sim\mathrm{Po}(m)X∼Po(m), the probability of exactly xxx events is P(X=x)=e−mmxx!P(X=x)=\frac{e^{-m}m^{x}}{x!}P(X=x)=x!e−mmx​, for x=0,1,2,…x=0,1,2,\dotsx=0,1,2,…. The factorial x!x!x! multiplies the whole numbers from xxx down to 1.

The cumulative probability P(X≤x)P(X\le x)P(X≤x) adds the probabilities of 0,1,…,x0,1,\dots,x0,1,…,x events. A calculator gives both P(X=x)P(X=x)P(X=x) and P(X≤x)P(X\le x)P(X≤x). For “at least”, use the complement: P(X≥x)=1−P(X≤x−1)P(X\ge x)=1-P(X\le x-1)P(X≥x)=1−P(X≤x−1).

Read the wording with care. “At most 3” means X≤3X\le3X≤3, “fewer than 3” means X≤2X\le2X≤2, and “more than 3” means X≥4X\ge4X≥4.

Worked example

Find Poisson probabilities

Calls arrive at a mean of 6 per hour, so X∼Po(6)X\sim\mathrm{Po}(6)X∼Po(6). Find the probability of exactly 4 calls in an hour, and of at least 2 calls.
  1. 1
    Formula: P(X=4)=e−6644!=1296 e−624=54e−6≈0.134P(X=4)=\frac{e^{-6}6^{4}}{4!}=\frac{1296\,e^{-6}}{24}=54e^{-6}\approx0.134P(X=4)=4!e−664​=241296e−6​=54e−6≈0.134.
  2. 2
    Complement: P(X≥2)=1−P(X≤1)=1−(e−6+6e−6)P(X\ge2)=1-P(X\le1)=1-\left(e^{-6}+6e^{-6}\right)P(X≥2)=1−P(X≤1)=1−(e−6+6e−6).
  3. 3
    Simplify: 1−7e−6≈1−0.01735≈0.9831-7e^{-6}\approx1-0.01735\approx0.9831−7e−6≈1−0.01735≈0.983.

Answer: P(X=4)≈0.134P(X=4)\approx0.134P(X=4)≈0.134 and P(X≥2)≈0.983P(X\ge2)\approx0.983P(X≥2)≈0.983.

Key terms · tap one for its definition

factorial

The factorial x!x!x! is the product of all positive whole numbers up to xxx, with 0!=10!=10!=1.

cumulative probability

The cumulative probability P(X≤x)P(X\le x)P(X≤x) is the probability that XXX takes the value xxx or any smaller value.

Part 3 done

4

Part 4 of 5: The mean and variance of a Poisson distribution are equal

Next, look at the centre and spread of the distribution. A Poisson distribution is fixed by one value, its mean. The variance equals the mean: E(X)=m\mathrm{E}(X)=mE(X)=m and Var(X)=m\mathrm{Var}(X)=mVar(X)=m.

The standard deviation is therefore m\sqrt{m}m​. If the sample mean and sample variance of count data differ greatly, a Poisson model is doubtful. A count with mean 4 and variance 4.2 is plausible for a Poisson model.

The mean scales with the period. If calls average 6 per hour, then m=3m=3m=3 for 30 minutes and m=12m=12m=12 for 2 hours.

Figure 1. The probabilities peak near the mean and tail off to the right.

Worked example

Scale the mean

Faults occur randomly along a cable at a mean of 0.8 per 10 m. Find the probability of no faults in 25 m, and the variance of the number of faults in 25 m.
  1. 1
    Scale the mean: m=0.8×2510=2.0m=0.8\times\frac{25}{10}=2.0m=0.8×1025​=2.0, so X∼Po(2.0)X\sim\mathrm{Po}(2.0)X∼Po(2.0).
  2. 2
    No faults: P(X=0)=e−2≈0.135P(X=0)=e^{-2}\approx0.135P(X=0)=e−2≈0.135.
  3. 3
    Variance: Var(X)=m=2.0\mathrm{Var}(X)=m=2.0Var(X)=m=2.0.

Answer: The probability of no faults is about 0.135 and the variance is 2.0.

Go deeperSums of Poisson counts

If X∼Po(m1)X\sim\mathrm{Po}(m_1)X∼Po(m1​) and Y∼Po(m2)Y\sim\mathrm{Po}(m_2)Y∼Po(m2​) are independent, then X+Y∼Po(m1+m2)X+Y\sim\mathrm{Po}(m_1+m_2)X+Y∼Po(m1​+m2​). This is why counts over two separate hours add their means.

A Poisson distribution also approximates a binomial distribution when the number of trials is large and the success probability is small.

Part 4 done

Quick check

One question on the part you just read

Easy

If X∼Po(4.5)X\sim\mathrm{Po}(4.5)X∼Po(4.5), state Var(X)\mathrm{Var}(X)Var(X).
Show answer and explanation

Answer: A · Worked explanation

For a Poisson distribution the variance equals the mean, so Var(X)=4.5\mathrm{Var}(X)=4.5Var(X)=4.5. The standard deviation is the square root of the variance, which is about 2.12. The value 20.25 comes from squaring the mean, and 9.0 comes from doubling it. Neither relationship holds for a Poisson distribution.
5

Part 5 of 5: Probabilities must be interpreted in the context of the situation

A calculated probability only helps when it is read in context. For the call centre, P(X=4)≈0.134P(X=4)\approx0.134P(X=4)≈0.134. This means that in about 13 hours out of every 100, exactly 4 calls arrive.

Suppose P(X≥10)≈0.0839P(X\ge10)\approx0.0839P(X≥10)≈0.0839. About 8 hours in every 100 bring 10 or more calls. A manager could use this to plan staffing. With a mean of 6, about six calls is typical, while 0 or 15 calls would be unusual.

A Poisson variable has no upper limit, so very large counts have a small but non-zero probability.

Exam tip

Answer in the words of the question. Name the event, the period, and the type of probability, such as “exactly” or “at least”.

Note read

Check your recall[14 marks]

6 written questions. Answer each one in your head or on paper, then open the mark scheme.

  1. 1.State[2 marks]

    State two conditions needed for a Poisson model.

    Show mark schemeHide mark scheme

    Model answer

    Events occur independently of each other, and they occur at a constant average rate. (Events occurring singly or counting over a fixed period are also acceptable.)

    • 1 mark for stating one valid condition, such as independent events
    • 1 mark for stating a second valid condition, such as a constant average rate, events one at a time, or a fixed period
  2. 2.Calculate[3 marks]

    Emails arrive at random with a mean of 2.5 per hour. Calculate the probability that exactly 3 emails arrive in one hour.

    Show mark schemeHide mark scheme

    Model answer

    X∼Po(2.5)X\sim\mathrm{Po}(2.5)X∼Po(2.5), so P(X=3)=e−2.52.533!=0.08208×15.6256≈0.214P(X=3)=\frac{e^{-2.5}2.5^{3}}{3!}=\frac{0.08208\times15.625}{6}\approx0.214P(X=3)=3!e−2.52.53​=60.08208×15.625​≈0.214.

    • 1 mark for identifying X∼Po(2.5)X\sim\mathrm{Po}(2.5)X∼Po(2.5)
    • 1 mark for substituting correctly into e−mmxx!\frac{e^{-m}m^{x}}{x!}x!e−mmx​
    • 1 mark for obtaining 0.214
  3. 3.Determine[3 marks]

    Emails arrive at a mean of 2.5 per hour. Determine the probability of at least one email in 30 minutes.

    Show mark schemeHide mark scheme

    Model answer

    For 30 minutes, m=1.25m=1.25m=1.25. Then P(X≥1)=1−P(X=0)=1−e−1.25≈1−0.2865=0.713P(X\ge1)=1-P(X=0)=1-e^{-1.25}\approx1-0.2865=0.713P(X≥1)=1−P(X=0)=1−e−1.25≈1−0.2865=0.713.

    • 1 mark for scaling the mean to 1.25
    • 1 mark for using the complement 1−P(X=0)1-P(X=0)1−P(X=0)
    • 1 mark for obtaining 0.713
  4. 4.Write down[1 mark]

    Write down the variance of XXX when X∼Po(7.5)X\sim\mathrm{Po}(7.5)X∼Po(7.5).

    Show mark schemeHide mark scheme

    Model answer

    The variance equals the mean, so Var(X)=7.5\mathrm{Var}(X)=7.5Var(X)=7.5.

    • 1 mark for stating that the variance is 7.5
  5. 5.Explain[2 marks]

    Explain why a Poisson model may be unsuitable for the number of customers entering a shop in a day when the shop is far busier at lunchtime.

    Show mark schemeHide mark scheme

    Model answer

    A Poisson model needs a constant average rate. Busier lunchtimes mean the rate changes through the day, so the condition fails.

    • 1 mark for stating that a constant average rate is required
    • 1 mark for linking the lunchtime peak to a changing rate
  6. 6.Discuss[3 marks]

    Weekly counts of an event have sample mean 4.1 and sample variance 9.8. Discuss whether a Poisson model is suitable.

    Show mark schemeHide mark scheme

    Model answer

    For a Poisson distribution the mean and variance are equal. Here the variance is much larger than the mean, so the model is doubtful. The events may not be independent, or the rate may change.

    • 1 mark for stating that a Poisson distribution has equal mean and variance
    • 1 mark for observing that the variance is far larger than the mean
    • 1 mark for concluding that the model is doubtful or suggesting a reason

Practice this topic

10 quick-fire multiple-choice questions, easy to hard. Tap an answer to see if you're right and the worked explanation. (The written questions with mark schemes are under “Check your recall” above.)

0 right0 of 10 answered

Includes the 2 quick checks in the note above.

3.

Easy·Calculate[1 mark]

For X∼Po(2)X\sim\mathrm{Po}(2)X∼Po(2), calculate P(X=0)P(X=0)P(X=0).
Show answer and explanation

Answer: A · Worked explanation

With x=0x=0x=0, the formula gives P(X=0)=e−2200!=e−2≈0.135P(X=0)=\frac{e^{-2}2^{0}}{0!}=e^{-2}\approx0.135P(X=0)=0!e−220​=e−2≈0.135, since 20=12^{0}=120=1 and 0!=10!=10!=1. The value 0.271 is P(X=1)=2e−2P(X=1)=2e^{-2}P(X=1)=2e−2, which would be the answer for exactly one event. The value 0.865 is P(X≥1)P(X\ge1)P(X≥1), the probability of at least one event. A quick check is that every Poisson probability lies between 0 and 1.
4.

Medium·Calculate[2 marks]

For X∼Po(3)X\sim\mathrm{Po}(3)X∼Po(3), calculate P(X=2)P(X=2)P(X=2).
Show answer and explanation

Answer: A · Worked explanation

Substitute into the formula: P(X=2)=e−3322!=92e−3=4.5×0.04979≈0.224P(X=2)=\frac{e^{-3}3^{2}}{2!}=\frac{9}{2}e^{-3}=4.5\times0.04979\approx0.224P(X=2)=2!e−332​=29​e−3=4.5×0.04979≈0.224. The value 0.423 is the cumulative probability P(X≤2)P(X\le2)P(X≤2), which adds the cases of 0, 1 and 2 events. The value 0.801 is P(X≥2)P(X\ge2)P(X≥2), the probability of two or more events. Keep the unrounded value of e−3e^{-3}e−3 until the final rounding.
5.

Medium·Calculate[2 marks]

Buses arrive at a stop at random, at a mean of 4 per hour. Calculate the probability that no bus arrives in a 15-minute period.
Show answer and explanation

Answer: A · Worked explanation

A rate of 4 buses per hour gives a mean of m=4×1560=1m=4\times\frac{15}{60}=1m=4×6015​=1 for a 15-minute period. Then P(X=0)=e−1≈0.368P(X=0)=e^{-1}\approx0.368P(X=0)=e−1≈0.368. The value 0.018 is e−4e^{-4}e−4, which wrongly keeps the hourly mean. The value 0.632 is the probability of at least one bus.
6.

Medium·Calculate[2 marks]

Errors appear at random on a website, at a mean of 1.5 per day. Calculate the probability of at least one error in a day.
Show answer and explanation

Answer: A · Worked explanation

Use the complement: P(X≥1)=1−P(X=0)=1−e−1.5≈1−0.223=0.777P(X\ge1)=1-P(X=0)=1-e^{-1.5}\approx1-0.223=0.777P(X≥1)=1−P(X=0)=1−e−1.5≈1−0.223=0.777. The value 0.223 is the probability of no errors, which is the quantity being subtracted. The value 0.558 is P(X≤1)P(X\le1)P(X≤1), which includes the case of no errors and so is not “at least one”.
7.

Medium·Identify[2 marks]

A Poisson model for text messages received in one hour gives P(X=0)=0.082P(X=0)=0.082P(X=0)=0.082. Identify the correct interpretation.
Show answer and explanation

Answer: A · Worked explanation

The value P(X=0)=0.082P(X=0)=0.082P(X=0)=0.082 is the probability of receiving no messages in one hour, so about 8 hours in every 100 have none. It is a probability, not a mean or a count of messages. The probability of exactly one message would be a different value, found from P(X=1)P(X=1)P(X=1).
8.

Hard·Identify[2 marks]

Counts from four sources are summarised by sample mean and sample variance. Identify the summary most consistent with a Poisson model.
Show answer and explanation

Answer: A · Worked explanation

A Poisson distribution has equal mean and variance, so a mean of 5.1 and a variance of 5.3 fit well. A variance of 26.0 is roughly the square of the mean, and a variance of 2.6 is half the mean; neither matches.
9.

Hard·Calculate[2 marks]

Faults occur randomly at a mean of 0.9 per hour. Calculate the probability of more than one fault in 2 hours.
Show answer and explanation

Answer: A · Worked explanation

For 2 hours the mean is m=0.9×2=1.8m=0.9\times2=1.8m=0.9×2=1.8. Then P(X≥2)=1−P(0)−P(1)=1−e−1.8(1+1.8)=1−2.8×0.1653≈0.537P(X\ge2)=1-P(0)-P(1)=1-e^{-1.8}(1+1.8)=1-2.8\times0.1653\approx0.537P(X≥2)=1−P(0)−P(1)=1−e−1.8(1+1.8)=1−2.8×0.1653≈0.537. The value 0.463 is P(X≤1)P(X\le1)P(X≤1), the opposite event. The value 0.228 comes from using m=0.9m=0.9m=0.9 without scaling to 2 hours. Always scale the mean to the length of the period before using the formula.
10.

Hard·Calculate[2 marks]

Calls arrive independently at a constant average rate of 3 per hour. Calculate the probability of exactly 2 calls in total across a 2-hour period.
Show answer and explanation

Answer: A · Worked explanation

Over 2 hours the mean is m=3×2=6m=3\times2=6m=3×2=6, because independent counts add their means. Then P(X=2)=e−6622!=18e−6≈0.0446P(X=2)=\frac{e^{-6}6^{2}}{2!}=18e^{-6}\approx0.0446P(X=2)=2!e−662​=18e−6≈0.0446. The value 0.224 keeps m=3m=3m=3 for one hour. The value 0.0502 is 0.22420.224^{2}0.2242, the probability of exactly 2 calls in each hour separately.

Keep going

Next topic4.18 Hypothesis testingPrevious topic4.16 Confidence intervals

More in Topic 4 · Statistics and probability

  1. 4.11Chi-squared and t-testsNotes · 10 questions
  2. 4.12Designing data collectionNotes · 10 questions· HL only
  3. 4.13Non-linear regressionNotes · 10 questions· HL only
  4. 4.14Linear combinations of random variablesNotes · 10 questions· HL only
  5. 4.15Central limit theoremNotes · 10 questions· HL only
  6. 4.16Confidence intervalsNotes · 10 questions· HL only
  7. 4.17Poisson distributionNotes · 10 questions· HL only
  8. 4.18Hypothesis testingNotes · 10 questions· HL only
  9. 4.19Transition matrices and Markov chainsNotes · 10 questions· HL only

All IB Mathematics: Applications and Interpretation topics →

Draft: written by Scribe and checked automatically, not yet by a subject reviewer.

Practice questions are original, written by Scribe and checked automatically for correctness.

Topic codes follow the official numbering. Not endorsed by IB Diploma Programme or any exam board.

On this page

0/5 read

  1. 1The Poisson distribution counts random events in a fixed period
  2. 2A Poisson model needs random, independent events at a steady rate
  3. 3Poisson probabilities come from one formula or a calculator
  4. 4The mean and variance of a Poisson distribution are equal
  5. 5Probabilities must be interpreted in the context of the situation
  6. Check your recall
  7. Practice: 10 questions
All coursesScribeHow it worksPricingPrivacyTerms

Notes and questions are written by Scribe in our own words. Topic codes follow the official course numbering so you can find your place. Not produced or endorsed by the IB, College Board, AQA, OCR, Pearson Edexcel or any exam board.

© 2026 Scribe

Poisson probabilities for a mean of 6

Probability P(X = x)0246810121400.050.10.15Number of calls in one hour, x
  • Mean m = 6