3 events per hour
mean wait 1/3 h = 20 min
1/λ.
If events occur as a Poisson process of rate , the gaps between successive events are independent exponential variables with rate and mean .
This page is easier if you are comfortable with:
Buses arrive at rate per hour. The mean gap is hour = 15 minutes. The chance that a gap exceeds 15 minutes is . The chance that the next bus arrives within 5 minutes ( hour) is . The probabilities use the exponential cdf (exponential cdf).
Why: the probability of no events in a time is the Poisson probability (the Poisson distribution, the Poisson process), and this is exactly the chance that the first gap exceeds . Because the process has no memory, you gain nothing by having waited already: the wait still has mean 15 minutes. The time to the th event is the sum of gaps, a gamma variable (the gamma distribution, sums of independent variables).
The pair of facts, counts Poisson and gaps exponential, is the basis of queueing models such as the M/M/1 queue (the M/M/1 queue) and of survival analysis (survival analysis). The rate is estimated by the reciprocal of the mean gap (the MLE of the exponential rate).
Gaps between random events at a steady rate are exponentially distributed.
Short gaps are the most likely, but long gaps do occur.
These examples are worked by hand, step by step, so you can compare your own working.
Find the mean gap in minutes for per hour.
Find .
Find .
A few situations come up again and again. Knowing them saves time and helps you spot answers that cannot be right.
mean wait 1/3 h = 20 min
1/λ.
e^(−1.5) = 0.2231
λt = 3 × 0.5.
1 − e⁻¹ = 0.6321
λt = 1.
number of events in time t ~ Po(λt)
P(0 events) = e^(−λt).
In a Poisson process with rate λ, the waiting time to the next event is exponential with mean 1/λ. P(wait > t) = e^(−λt), which equals the Poisson probability of zero events in time t.
Events occur at 3 per hour. Find the mean waiting time in minutes.
Find P(wait > 30 minutes).
Find P(an event within 20 minutes).
Show P(wait > 0.5) equals P(Po(1.5) = 0).
λ = 3 per hour with t = 30 ✗
t = 0.5 hours ✓
Match the units.
3 ✗
1/λ ✓
Invert the rate.
e^(−1.5) ✗
1 − e^(−1.5) ✓
That is survival.
time already waited changes the odds ✗
it does not ✓
Poisson processes have no memory.
Try each one on paper, then open the answer. Use the solver above to see the full working.
10
0.3679
0.6321
0.3679
4
0.1353
Unlimited fresh questions with instant marking. Choose a level, work it out on paper, then type your answer.
Solve: …
Exponential with rate λ.
1/λ.
P(wait > t) = P(Po(λt) = 0).
No, it is memoryless.
exponential CDF.
sum of Poisson variables.
More in Advanced statistics and stochastic processes and the formula sheets.