The Poisson distribution models the number of times an event happens in a fixed interval of time or space when the events occur independently and at a constant average rate λ. Typical examples are calls to a call centre per hour, emails per day, typos per page, goals in a football match, meteor sightings per night or mutations per DNA segment.
A single number describes it: λ is both the mean and the variance, so the standard deviation is √λ. For small λ the distribution is strongly skewed with a big chance of zero events; as λ grows it becomes more symmetric and approaches a normal curve. It is also the limit of the binomial distribution when the number of trials is large and the success probability small, with λ = n·p.
Enter the average rate for your interval (if you know a rate per hour but care about 30 minutes, halve it first) and the number of events k. The calculator returns all five kinds of probability, highlights the matching bars and lists the summary measures.
How to use the Poisson Distribution Calculator
- Average rate λ (events per interval)
- Number of events (k)
- Probability of
Everything is calculated in your browser, so results appear instantly and nothing you type is sent to a server.
How it works
P(X = k) is computed with logarithms (λᵏ and k! overflow quickly) and the cumulative probability adds the terms from 0 to k. “At least” and “more than” are complements of the cumulative values.
Worked example
A help desk receives on average 4 calls per hour. The probability of exactly 2 calls in an hour is e^(−4) × 16/2 = 14.65%, of at most 2 calls 23.81%, and of more than 5 calls 21.49%. The chance of a quiet hour with no calls is e^(−4) = 1.83%. With λ = 5, the probability of exactly one event is 5e^(−5) = 3.37%.
Poisson probabilities for small λ
| k | λ = 1 | λ = 2 | λ = 4 |
|---|---|---|---|
| 0 | 36.79% | 13.53% | 1.83% |
| 1 | 36.79% | 27.07% | 7.33% |
| 2 | 18.39% | 27.07% | 14.65% |
| 3 | 6.13% | 18.04% | 19.54% |
| 4 | 1.53% | 9.02% | 19.54% |
| 5 | 0.31% | 3.61% | 15.63% |
Formula
P(X = k) = e^(−λ) λᵏ ÷ k! · P(X ≤ k) = Σ e^(−λ) λⁱ/i! for i = 0…k · mean = variance = λ · SD = √λ
Worked example
Inputs: Average rate λ (events per interval): 4; Number of events (k): 2; Probability of: Exactly k – P(X = k).
Results: Requested probability = 14.6525 %; P(X = k) = 14.6525 %; P(X ≤ k) = 23.8103 %; P(X ≥ k) = 90.8422 %; P(X < k) = 9.1578 %; P(X > k) = 76.1897 %.
Key terms
- Rate (λ)
- The average number of events in the interval; it is both the mean and the variance.
- Poisson process
- Events occurring independently at a constant average rate.
- Cumulative probability
- P(X ≤ k), the probability of k or fewer events.
Frequently asked questions
When can I use the Poisson distribution?
When events are counted in a fixed interval, happen independently, one at a time, and at a constant average rate.
What is P(X = 2) when λ = 4?
e^(−4) × 4² / 2! = 14.65%; at most 2 events is 23.81%.
What is special about the Poisson distribution?
Its mean and variance are both λ. If your counts vary much more than their mean, a negative binomial model fits better.
When does it approximate the binomial?
When n is large and p small (say n ≥ 20 and p ≤ 0.05); use λ = n·p.
What if my rate is for a different interval?
Scale it: 6 calls per hour means λ = 3 for a 30-minute window.
What is the chance of no events?
e^(−λ). With 3 events expected, P(0) = 4.98%.
Does λ have to be a whole number?
No. λ is an average and can be any positive number, but k must be a whole number.