Poisson Process Explained with Worked Examples

In a Poisson process with rate , the number of events in time is Poisson with mean : , and the waiting time between events is exponential with rate .

Write 2x or 2*x to multiply, ^ for powers, and ; between simultaneous equations. You can also type factor, expand, derivative of, integrate … from a to b, limit … as x->0 or 15% of 80.

Try an example

Before you start

This page is easier if you are comfortable with:

What Poisson process means

If calls arrive at per hour, in hours the mean is 6 and . The probability of no call in one hour is , and the chance that the next call takes more than half an hour is (the Poisson distribution, the exponential distribution).

Events in disjoint intervals are independent, and the process has no memory: the time to the next event does not depend on how long we have already waited. The time to the th event is a gamma (Erlang) variable (the gamma distribution). The mean and variance of the count are both (mean and variance of a Poisson variable); superposing independent Poisson processes gives another with the summed rate (sums of independent Poisson variables).

Waiting-time details are in exponential waiting times. The process is the simplest continuous-time Markov chain and is the arrival model of queues (the M/M/1 queue). Its counting probabilities come from the limit of binomial counts (the Poisson approximation).

What is it used for?

The Poisson process models events that occur at random at a steady average rate.

How to use poisson process

  1. Identify the rate and the time .
  2. The count has mean .
  3. Use for exact counts.
  4. Use for waiting longer than .

Graph

Probability of n events in 3 hours at rate 2 per hour (mean 6)n = 4: 0.133902468101200.020.040.060.080.10.120.140.160.180.2Probability of n events in 3 hours at rate 2 per hour (mean 6)nprobabilityGraph with x from 0 to 12 and y from 0 to 0.2. Shows P(N = n) (11); point n = 4: 0.1339 at (4, 0.1339).

The counts peak around the mean 6.

Worked examples

These examples are worked by hand, step by step, so you can compare your own working.

Example 1: four calls in 3 hours

Find for .

Worked example
Answer
0.13390.1339
  1. Mean
  2. Probability

Example 2: waiting more than 30 minutes

Find for per hour.

Worked example
Answer
0.36790.3679
  1. Formula

Example 3: no events

Find for .

Worked example
Answer
0.13530.1353
  1. Formula

Special cases

A few situations come up again and again. Knowing them saves time and helps you spot answers that cannot be right.

λ = 3/hr, t = 2

mean count 6

N(2) ~ Poisson(6).

P(N = 4)

e⁻⁶ 6⁴/4!

0.1339.

P(no event in 30 min)

e^(−1.5)

0.2231.

Mean waiting time

1/λ

0.3333 hr.

Word problems

In a Poisson process of rate λ, N(t) ~ Poisson(λt) and the waiting times between events are independent Exp(λ) with mean 1/λ.

Mean count

λ = 3 per hour, t = 2 hours. Find λt.

  1. 3 × 2
  2. Check: ✓6

Exactly four

Find P(N(2) = 4).

  1. e⁻⁶ × 1296/24
  2. Check: ✓0.1339

None in half an hour Higher

Find P(N(0.5) = 0).

  1. e^(−1.5)
  2. Check: ✓0.2231

Waiting time Higher

Find the mean waiting time.

  1. 1/3
  2. Check: ✓0.3333

Common mistakes

Forgetting t

Poisson(λ) ✗

Poisson(λt) ✓

Scale with time.

Waiting time λ

mean λ ✗

mean 1/λ ✓

Inverse.

Overlapping intervals independent

assume ✗

only disjoint intervals ✓

Independent increments.

Variable rate

constant rate ✗

inhomogeneous ✓

Different model.

Exam tips

  1. N(t) ~ Poisson(λt).
  2. Gaps ~ Exp(λ).
  3. Disjoint intervals independent.
  4. P(0) = e^(−λt).
  5. Units consistent.

Practice questions

Try each one on paper, then open the answer. Use the solver above to see the full working.

1. λt for λ = 4, t = 1.5 Foundation

6

2. P(N = 0), λt = 2 to 4 d.p. Foundation

0.1353

3. P(N = 1), λt = 2 to 4 d.p. Foundation

0.2707

4. Mean gap for λ = 5 Higher

0.2

5. P(N = 2), λt = 3 to 4 d.p. Higher

0.224

6. P(N = 3), λt = 1 to 4 d.p. Higher

0.0613

Practice generator

Unlimited fresh questions with instant marking. Choose a level, work it out on paper, then type your answer.

Solve: …

Key terms

Poisson process
Events at rate λ.
Rate (λ)
Events per unit time.
Inter-arrival time
Gap between events.
Independent increments
Disjoint counts independent.
Memoryless
Exponential gaps.
Counting process
N(t).

Frequently asked questions

What is a Poisson process?

A random stream of events at constant rate λ.

What is the distribution of N(t)?

Poisson(λt).

What are the waiting times?

Exponential with rate λ.

What is P(no events)?

e^(−λt).

Which page covers the Poisson MGF?

MGF of the Poisson.

Which page covers Markov chains?

Markov chain stationary distribution.

More in Advanced statistics and stochastic processes and the formula sheets.