Poisson Distribution Calculator

A Poisson distribution calculator for counts of events in a fixed interval — calls per hour, emails per day, accidents per week. Enter the average rate λ and the number of events k to get the exact probability, cumulative probabilities, mean, variance and a bar chart of the distribution, with every step shown.

Enter your values

Counts of events in a fixed interval, with a known average rate.

The mean number of events expected in one interval. Must be greater than 0.

Same unit both sides, e.g. λ = 2 per 1 hour, calculate for 8 hours → λ = 16.

k is a whole number: 0, 1, 2, 3, …

P(X = 2)

14.65%

For λ = 4, the chance of exactly 2 events is about 0.1465.

0.1465P(X = k)
0.2381P(X ≤ k)
0.9084P(X ≥ k)
4Mean (μ = λ)
4Variance (σ² = λ)
2Standard deviation (√λ)
4Mode (⌊λ⌋)
4Effective λ
—Range P(a≤X≤b)

Probability mass function — P(X = k) for λ = 4

The tallest bar is at the mode. For a Poisson distribution the mean and the variance are both equal to λ, so the bars spread out as λ grows.

How the probability is worked out

    kP(X = k)P(X ≤ k)

    A Poisson distribution calculator finds the probability of a number of events in a fixed interval when events happen at a known average rate λ. Enter λ and k to get P(X = k) = λk · e−λ / k!, with cumulative probabilities, mean λ, variance λ and a bar chart. Use it for calls, arrivals, defects and rare-event counts.

    What is a Poisson distribution?

    A Poisson distribution is a discrete probability distribution for the number of times an event happens in a fixed interval of time or space, when events occur one at a time, independently, at a constant average rate. It answers questions such as: how likely are exactly 3 calls in the next hour, or at most 1 defect in a batch?

    It is the right model when three conditions hold: events happen singly, not in clusters at the same instant; events are independent of one another; and the average rate λ does not change over the interval. When those conditions fail — for example, when the rate varies through the day — the Poisson model can mislead and a different model is needed.

    Typical uses include calls arriving at a call centre, emails reaching an inbox, accidents on a stretch of road, defects on a production line and website visits per minute. The distribution is named after Siméon Denis Poisson, who introduced it in 1837.

    The Poisson distribution is also the limit of the binomial distribution when the number of trials n is large and the probability of success p is small, with λ = n × p held fixed. That is why Poisson probabilities work well for rare events counted over many trials — try the same question in our binomial probability calculator to compare the two answers.

    Poisson distribution formula

    For a Poisson random variable X with rate λ, the probability of exactly k events is P(X = k) = λk · e−λ / k!, for k = 0, 1, 2, …. Here e ≈ 2.71828 is Euler’s number, λk is the rate raised to the power k, and k! is k factorial — for example, 3! = 3 × 2 × 1 = 6.

    Cumulative probabilities are sums of single probabilities. P(X ≤ k) adds P(X = 0) through P(X = k), and P(X ≥ k) equals 1 − P(X ≤ k − 1). The calculator above shows both, so you do not need to add long sums by hand.

    Worked example — λ = 4, k = 2: P(X = 2) = 42 · e−4 / 2! = 16 × 0.018316 / 2 = 0.1465. There is about a 14.65% chance of exactly 2 events. The mean is 4, the variance is 4 and the standard deviation is √4 = 2 — see our standard deviation calculator for the general method.

    One property sets the Poisson distribution apart: its mean and its variance are both equal to λ. A larger λ therefore shifts the distribution to the right and spreads it out at the same time. If your data have a variance much larger than their mean, the Poisson model is probably the wrong choice.

    When to use a Poisson vs binomial distribution?

    Short answer: use the Poisson distribution when you count events in a fixed interval and only know the average rate; use the binomial distribution when you have a fixed number of independent trials and know the probability of success in each trial.

     Poisson distributionBinomial distribution
    What is countedEvents in a fixed intervalSuccesses in n trials
    What you knowAverage rate λNumber of trials n and probability p
    Number of trialsNot fixed — the count variesFixed at n
    Typical questionExactly, at most or at least k events?Exactly, at most or at least k successes?
    ExampleCalls in an hourHeads in 10 coin tosses

    When n is large, p is small and λ = n × p, the two models give almost the same answers — the Poisson distribution is the limit of the binomial in that case. For a problem with a fixed number of trials, such as 20 patients or 10 coin tosses, the binomial is the exact model; for arrivals and counts over time, the Poisson model is the natural one. For larger counts, the normal approximation to the binomial is another way to check the result.

    See more worked comparisons in our Poisson distribution examples.

    What does λ mean in a Poisson distribution?

    λ (lambda) is the average rate — the mean number of events expected in the interval you are measuring. If a shop gets 2 customers per hour on average, λ = 2 per hour. It is both the centre of the distribution and its spread: the mean is λ and the variance is λ, so the standard deviation is √λ.

    λ scales with the interval. The calculator’s rate-scaling option does this for you: a rate of 2 per hour becomes λ = 2 × 8 = 16 over an 8-hour shift, and P(X = 16) is then about 0.0992. Halve the interval and λ halves; double it and λ doubles. Always state the interval λ belongs to — a bare number without its interval is meaningless.

    As λ grows, the distribution flattens and becomes more symmetric, approaching the shape of a normal distribution — which is why large-λ Poisson probabilities can be approximated with a normal curve.

    Poisson distribution examples

    Four short worked examples show how the calculator handles the most common cases. Each one can be repeated with the Try buttons above the results.

    Example 1: No events at all — λ = 3, k = 0

    A website averages 3 visits per minute. What is the chance of no visits in a minute? P(X = 0) = e−3 = 0.0498, about 4.98%. The chance of at most 1 visit is P(X ≤ 1) = 0.0498 + 0.1494 = 0.1991, about 19.91%.

    Example 2: A fractional rate — λ = 2.5, k = 3

    A machine averages 2.5 faults per day. The chance of exactly 3 faults tomorrow is P(X = 3) = 2.53 · e−2.5 / 3! = 15.625 × 0.082085 / 6 = 0.2138, about 21.38%. The mean is 2.5, the variance is 2.5, the standard deviation is √2.5 ≈ 1.581 and the mode is 2.

    Example 3: A rare event — λ = 0.5, k = 0

    Floods average 0.5 per year in a town. The chance of no flood in a year is P(X = 0) = e−0.5 = 0.6065, about 60.65%, so the chance of at least one flood is P(X ≥ 1) = 1 − 0.6065 = 0.3935, about 39.35%.

    Example 4: Scaling the rate — 2 per hour over an 8-hour shift

    A help desk averages 2 calls per hour. Over an 8-hour shift the rate scales to λ = 2 × 8 = 16, and the chance of exactly 16 calls in the shift is P(X = 16) = 0.0992, about 9.92%. Tick the Scale λ to a different interval box in the calculator to do this automatically.

    For a longer set of step-by-step problems, see our worked Poisson examples and, for the fixed-trials case, the binomial distribution examples.

    Frequently asked questions

    What is the Poisson distribution formula?

    P(X = k) = λk · e−λ / k!, where λ is the average rate, k is the number of events, e ≈ 2.71828 and k! is k factorial. The calculator above applies the formula and shows each step.

    When should I use a Poisson distribution instead of a binomial distribution?

    Use the Poisson distribution when you count events in a fixed interval and know only the average rate; use the binomial distribution when you have a fixed number of trials n and a probability of success p per trial. When n is large and p is small, with λ = n × p, the two give nearly the same result.

    What is λ in a Poisson distribution?

    λ is the average number of events expected in the interval — the rate. For example, λ = 3 per hour means 3 events per hour on average. It is also the mean and the variance of the distribution.

    What are the mean and variance of a Poisson distribution?

    Both are λ. The mean is λ, the variance is λ and the standard deviation is √λ. For λ = 4, the mean and the variance are both 4 and the standard deviation is 2.

    How do I calculate P(X = 0)?

    P(X = 0) = e−λ. For λ = 3, that is e−3 ≈ 0.0498, about 4.98%.

    Can λ be a decimal?

    Yes. λ is an average, so it can be any positive number, including decimals such as 2.5 or 0.5. The count k, by contrast, must be a whole number.

    What is the mode of a Poisson distribution?

    The mode is ⌊λ⌋, the largest whole number not greater than λ. For λ = 2.5 the mode is 2; for λ = 4 the mode is 4 (and, because λ is a whole number, 3 is also a mode).

    How do I scale a Poisson rate to a longer interval?

    Multiply λ by the ratio of the new interval to the old one. A rate of 2 per hour becomes λ = 2 × 8 = 16 over an 8-hour shift. Use the calculator’s rate-scaling option to do it automatically.

    Source: NIST/SEMATECH e-Handbook of Statistical Methods, Poisson Distribution.