POISSON DISTRIBUTION
DISCRETE PROBABILITY DISTRIBUTION
INTRODUCTION OF POISSON DISTRIBUTION
• Poisson distribution is applied in situations where there are a large number of independent
Bernoulli trials with a very small probability of success in any trial say p.
• X : no of outcomes per “any interval”, Probability mass function of Poisson distribution
𝑒 −𝜇 𝜇 𝑥
𝑃 𝑥, 𝜇 = 𝑥 = 0, 1, 2, 3, … , ∞
𝑥!
𝜇 = 𝜆𝑡
Average = 𝜆 and t = time interval Poisson process
• The limiting case of binomial when n is very large and p is small but np is a positive number
which is called lambda.
lim 𝑏(𝑥: 𝑛, 𝑝) ~𝑃(𝑥: 𝜇 = 𝑛𝑝)
𝑛→∞
𝑝→0
Normally, for this approximation it is required that 𝑛 ≥ 50 𝑎𝑛𝑑 𝑝 ≤ 0.1
EXAMPLES OF POISSON DISTRIBUTION
A partial list of recently studied phenomena that obey a Poisson distribution is below:
the number of mutations on a given strand of DNA per time unit
the number of bankruptcies that are filed in a month
the number of arrivals at a car wash in one hour
the number of network failures per day
the number of file server virus infection at a data centre during a 24-hour period
the number of Airbus 330 aircraft engine shutdowns per 100,000 flight hours
the number of asthma patient arrivals in a given hour at a walk-in clinic
the number of hungry persons entering McDonald's restaurant per day
the number of work-related accidents over a given production time
the number of birth, deaths, marriages, divorces, suicides, and homicides over a given period of time
the number of customers who call to complain about a service problem per month
the number of visitors to a web site per minute
the number of calls to consumer hot line in a 5-minute period
the number of telephone calls per minute on your cell phone.
Example 1: Suppose you will be fishing for two hours, at a spot in which on average people catch 3 fishes per
hour. Then the number of fishes X you will catch is a random variable which is Poisson distributed .
Find the probability of catching 10 fishes for two hours.
𝜇 = 𝜆𝑡
Average = 𝜆 = 3 and t = 2
𝜇 =2×3=6
𝑒 −𝜇 𝜇𝑥
𝑃 𝑥, 𝜇 = 𝑥 = 0, 1, 2, 3, … , ∞
𝑥!
𝑒 −6 6𝑥
𝑃 𝑥, 𝜇 = 6 = 𝑥 = 0, 1, 2, 3, … , ∞
𝑥!
𝑒 −6 610
Formula Method: 𝑃 𝑋 = 10 =
10!
Table Method: 732-734 𝑃 𝑋 = 10 = 𝐹 10 − 𝐹 9 𝜇 = 6 𝑟 = 10 𝑎𝑛𝑑 𝑟 = 9
𝑃 𝑋 = 10 = 0.9574 − 0.9161
Example 2: Suppose the average number of lions seen on a 1-day safari is 5. What is the probability that
tourists will see fewer than four lions on the next 1-day safari?
𝜇 =5
𝑒 −𝜇 𝜇𝑥
𝑃 𝑥, 𝜇 = 𝑥= 0, 1, 2, 3, … , ∞
𝑥!
𝑒 −5 5𝑥
𝑃 𝑥, 𝜇 = 5 = 𝑥 = 0, 1, 2, 3, … , ∞
𝑥!
Formula Method: 𝑃 𝑋 < 4 = 𝑃 𝑋 = 0 + 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2 + 𝑃 𝑋 = 3
3
𝑒 −5 5𝑥
𝑥!
𝑥=0
Table Method: 732-734 𝑃 𝑋 < 4 = 𝐹 3 𝜇 = 5 𝑎𝑛𝑑 𝑟 = 3
𝑃 𝑋 < 4 = 0.2650
Example 3 :
one nanogram of plutonium-239 will have an average of 2.5 radioactive decays per second, and the number of
decays will follow a poisson distribution.
What is the probability that in a 2 second period there are at least 6 radioactive decays?
𝜇 = 𝜆𝑡
𝜇 = 2.5 × 2 = 5
𝑒 −5 5𝑥
𝑃 𝑥, 5 = 𝑥 = 0,1,2, … , ∞
𝑥!
𝑃 𝑋 ≥6 =1−𝑃 𝑋 <6
Formula method
=1− 𝑃 𝑋 =0 +𝑃 𝑋 =1 +𝑃 𝑋 =2 +𝑃 𝑋 =3 +𝑃 𝑋 =4 +𝑃 𝑋 =5
𝑒 −5 50 𝑒 −5 51 𝑒 −5 52 𝑒 −5 53 𝑒 −5 54 𝑒 −5 55
=1− + + + + +
0! 1! 2! 3! 4! 5!
Table Method
𝑃 𝑋 ≥6 =1−𝑃 𝑋 <6
= 1 − F 5 = 1 − 0.6160
For practice 2:
On average rate of 5 demands per week at a garage for replacement windscreens occurs randomly. Determine the
probability that no more than 7 demands for windscreen are demanded in next week.
Example 4 :
The windscreen manufacturer uses glass which contains random flaws at an average rate of 1.5 per 50 𝑚2 . A windscreen of area
150 𝑚2 is chosen at random. Determine the probability that the windscreen has fewer than 6 flaws.
𝜇 = 𝜆𝑡
𝜇 = 1.5 × 3 = 4.5
𝑒 −4.5 4.5𝑥
𝑃 𝑥, 4.5 = 𝑥 = 0,1,2, … , ∞
𝑥!
𝑃 𝑋 < 6 = 𝑃(𝑋 ≤ 5)
Formula method
=𝑃 𝑋 =0 +𝑃 𝑋 = 1 +𝑃 𝑋 =2 +𝑃 𝑋 =3 +𝑃 𝑋 =4 +𝑃 𝑋 = 5
𝑒 −4.5 4.50 𝑒 −4.5 4.51 𝑒 −4.5 4.52 𝑒 −4.5 4.53 𝑒 −4.5 4.54 𝑒 −4.5 4.55
= + + + + +
0! 1! 2! 3! 4! 5!
Table Method
𝑃 𝑋 < 6 = F 5 = 0.7029
For practice :
At a theme park, there is a roller coaster that send an average of 1.5 cars through its circuit every minute between 6:00 pm
and 7:00 pm. A random variable X: represents the number of rollers coaster cars to pass through the circuit system between
6:00pm and 6:10pm. What is the probability that more than 25 cars will pass through the circuit between 6:00 pm and 6:10
pm. 𝜇 = 𝜆𝑡
𝜇 = 1.5 × 10 = 15
𝑒 −15 15𝑥
𝑃 𝑥, 15 = 𝑥 = 0,1,2, … , ∞
𝑥!
𝑃(𝑋 > 25) (Find it your self)
Approximation of Binomial Distribution by a Poisson Distribution
For practice Example 5.19, 5.20
5.62
The probability that a student at a local high school fails the screening test for scoliosis (curvature of the spine) is
known to be 0.004. Of the next 1875 students at the school who are screened for scoliosis,
find the probability that
(a) fewer than 5 fail the test
𝑛 = 1875 𝑎𝑛𝑑 𝑝 = 0.004
𝜇 = 𝑛𝑝 = 1875 × 0.004 = 7.5
𝑒 −𝜇 𝜇𝑥
𝑃 𝑥, 𝜇 = 𝑥 = 0, 1, 2, 3, … , ∞
𝑥!
−7.5
𝑒 7.5𝑥
𝑃 𝑥, 𝜇 = 7.5 = 𝑥 = 0, 1, 2, 3, … , ∞
𝑥!
𝑃 𝑋 < 5 = 𝑃(𝑋 ≤ 4)
Formula method
𝑃 𝑋 <5 =𝑃 𝑋 =0 +𝑃 𝑋 =1 +𝑃 𝑋 = 2 +𝑃 𝑋 =3 +𝑃 𝑋 =4
𝑒 −4.5 4.50 𝑒 −4.5 4.51 𝑒 −4.5 4.52 𝑒 −4.5 4.53 𝑒 −4.5 4.54
= + + + +
0! 1! 2! 3! 4!
Table Method
𝐹 4 = 0.1321
(b) 8, 9, or 10 fail the test.
Formula method
𝑒 7.5 7.58 𝑒 −7.5 7.59 𝑒 −7.5 7.510
𝑃 8 ≤ 𝑋 ≤ 10 = 𝑃 𝑋 = 8 + 𝑃 𝑋 = 9 + 𝑃 𝑋 = 10 = + +
8! 9! 10!
Table Method
𝐹 8 ≤ 𝑋 ≤ 10 = 𝐹 10 − 𝐹 7 = 0.8622 − 0.5246
Example for practice 4:
1. In a treatment of hay fever, the probability that any sufferer is allergic to a particular drug is 0.0005.
Assuming that the occurrences of the allergy in different sufferers are independent. Find the
probability that in a random sample of 8000 sufferers more than 6 will be allergic to the drug.
𝑛 = 8000 𝑎𝑛𝑑 𝑝 = 0.0005
𝜇 = 𝑛𝑝 = 8000 × 0.0005 = 4
𝑒 −𝜇 𝜇𝑥
𝑃 𝑥, 𝜇 = 𝑥 = 0, 1, 2, 3, … , ∞
𝑥!
𝑒 −4 4𝑥
𝑃 𝑥, 𝜇 = 4 = 𝑥 = 0, 1, 2, 3, … , ∞
𝑥!
Formula Method: 𝑃 𝑋 > 6 = 𝑃 𝑋 = 7 + 𝑃 𝑋 = 8 + ⋯ + ∞
∞
𝑒 −4 4𝑥
𝑥!
𝑥=6
Table Method: 732-734 𝑃 𝑋 > 6 = 1 − 𝐹 6 𝜇 = 4 𝑎𝑛𝑑 𝑟 = 6
𝑃 𝑋 > 6 = 1 − 0.8893
Properties of Poisson Distribution:
1. Mean E(x) of Poisson distribution is equal to 𝜇 = 𝜆𝑡
2. Variance 𝜎𝑋2 of Poisson distribution is also equal to 𝜇 = 𝜆𝑡
3. Both the mean and the variance of the Poisson distribution p(x; 𝜇 = 𝜆𝑡) are equal.
𝐸(𝑋) = 𝜎𝑋2
𝑛 = 8000 𝑎𝑛𝑑 𝑝 = 0.0005 𝑞 = 1 − 0.0005 = 0.9995~1
𝐸 𝑋 = 𝑛𝑝 = 8000 × 0.0005 = 4
𝜎𝑋2 = 𝑛𝑝𝑞 = 8000 × 0.0005 × 1 = 4
5.57, 5.58, 5.60, 5.61, 5.62, 5.65, 5.66, 5.67,
5.69
