Overview
The Poisson distribution models how many times an event happens in a fixed interval, when events occur independently at a steady average rate, such as calls per hour or defects per batch.
Enter the average rate λ, the target count k and a mode: 1 exactly k, 2 at least k, or 3 at most k.
Worked examples
| Inputs | Result |
|---|---|
| Expected Rate (λ)3.8Target Count (k)5Probability ofExactly | P(X = 5): 14.77%Mean and variance (Poisson): 3.8 |
Show 3 more examples
| Expected Rate (λ)2Target Count (k)0Probability ofExactly | P(X = 0): 13.53%Mean and variance (Poisson): 2 |
| Expected Rate (λ)10Target Count (k)15Probability ofAt least | P(X >= 15): 8.35%Mean and variance (Poisson): 10 |
| Expected Rate (λ)5Target Count (k)3Probability ofAt most | P(X <= 3): 26.5%Mean and variance (Poisson): 5 |
P(X = 5) by expected rate
With the calculator's starting values, the P(X = 5) is 14.77%. The table shows how it changes with the expected rate.
| Expected Rate (λ) | P(X = 5) |
|---|---|
| 2 | 3.61% |
| 2.5 | 6.68% |
| 3 | 10.08% |
| 3.5 | 13.22% |
| 3.8starting value | 14.77% |
| 4 | 15.63% |
| 4.5 | 17.08% |
| 5 | 17.55% |
| 5.5 | 17.14% |
Other inputs: Target Count: 5 k. Change them in the calculator above for your own numbers.
How it works
P(X = k) = e^(−λ) × λ^k ÷ k!. The CDF adds the chances from 0 to k. Its mean and variance both equal λ. If your counts vary more than the mean, a negative binomial model may fit better.
The formula
| λ | Average number of events per interval |
Practical tips
- With λ = 3.8, the chance of exactly 5 is 14.77%.
- The chance of zero events is e^(−λ), so 2.24% here.
- Scale λ to your interval. 3.8 an hour is 1.9 per half hour.
Frequently asked questions
When does Poisson apply?
When events are independent and the average rate is steady.
What's the difference from binomial?
Binomial has a fixed number of trials. Poisson counts events with no fixed maximum.
Why are the mean and variance equal?
It's a defining property of the Poisson distribution.