You are on page 1of 30

Poisson Distribution

& Its Applications


By-
Snehil Mishra,
Simran,
Sandhya Upadhyaya,
Shashank Tiwari,
Priyanka Jarwal
What is Poisson
Distribution?
In statistics,
a “Poisson distribution” is a probability distribution that can be used to
show how many times an event is likely to occur within a specified period
of time.
Understanding Poisson Distribution
The Poisson distribution is a discrete function, meaning that the variable can
only take specific values in a (potentially infinite) list.

Put differently, the variable cannot take all values in any continuous range.
A Poisson distribution can be used to
estimate how likely it is that something For example,
will happen "X" number of times. if the average number of people who
rent movies on a Friday night at a
single video store location is 400.
A Poisson distribution can answer
such questions as……

"What is the probability that more than 600 people will rent movies?"
One of the most famous historical, practical uses of the Poisson distribution was
estimating the annual number of Prussian cavalry soldiers killed due to horse-
kicks.

Other modern examples include estimating the number of car crashes in a city of
a given size.
History of the
Poisson Distribution!!
Like many statistical tools and probability metrics, the Poisson Distribution was
originally applied to the world of GAMBLING.

-Simeon Denis Poisson(French Mathematician), 1830


In 1830, Simeon developed the distribution to indicate the low to high spread of
the probable number of times that a gambler would win at a gambling game-
such as baccarat- within a large number of times that the game was played.

Unfortunately, the gamblers paid no heed to Poisson’s prediction of the


probabilities of his obtaining only a certain number of wins, and lost heavily.
Classical Horse Kick Data
In 1898, a Russian economist
and statistician,
Ladislaus Josephovich Bortkie
wicz
, published an interesting
findings about the probability
distribution of Prussian
soldiers accidentally killed by
horse-kick.
WW II London bombings
In 1946, a British statistician, R.D.
Clarke, published his analysis of
the distribution of bomb hits by
flying bombs in London during
World War II.
When is Poisson
Distribution valid?
When to use Poisson Distribution in Finance?

The Poisson distribution is


commonly used to model financial
count data where the tally is small
and is often zero.
The Poisson Distribution is only a valid probability analysis tool under certain conditions

The following conditions must exist:

1. About the values that “k” can take

2. No occurrence of the event being analyzed affects the probability


of the event recurring (events occur independently)
Explaining the “independent” condition:

Number of meteors seen can be modeled as a Poisson distribution because the meteors are independent,
the average number of meteors per hour is constant

Rate parameter= number of events/interval * interval length

Let’s expect, 5 meteors per hour on average or 1 every 12 minutes, here λ=5

Now to see the probability of 3 meteors per hour i.e.


x=3, we’ll use the poisson distribution formula
Observation:
Probability of seeing exactly 3 meteors in one hour= 14%
or about 1/7

Implication
Other conditions:
3. There must be some interval of time

4. Proportionality

5. The number of trials

Given the above conditions, then k is a random variable, and the distribution of k
is a Poisson Distribution.
Calculating the Poisson Distribution

Where:
● The symbol “!” is a factorial.
● μ (the expected number of occurrences) is sometimes written as λ. Sometimes called
the event rate or rate parameter.
Example question

The average number of major storms in your city is 2 per year. What is the probability that
exactly 3 storms will hit your city next year?

Step 1: Figure out the components you need to put into the equation.

μ = 2 (average number of storms per year, historically)


x = 3 (the number of storms we think might hit next year)
e = 2.71828 (e is Euler’s number, a constant)
Step 2: Plug the values from Step 1 into the Poisson distribution formula:

P(x; μ) = (e-μ) (μx) / x!


= (2.71828 – 2) (23) / 3!
= (0.13534) (8) / 6
= 0.180

The probability of 3 storms happening next year is 0.180, or 18%

As you can probably tell, you can calculate the Poisson distribution manually but that
would take an extraordinary amount of time unless you have a simple set of data. The usual
way to calculate a Poisson distribution in real life situations is with software like IBM SPSS.
Business Uses of Poisson
Distribution!!
1) Calls per Hour at a Call Center

For example, suppose a given call center


receives 10 calls per hour.
P(X = 0 calls) = 0.00005
P(X = 1 call) = 0.00045
P(X = 2 calls) = 0.00227
P(X = 3 calls) = 0.00757
2) Number of Arrivals at a Restaurant

For example, suppose a given restaurant


receives an average of 100 customers per
day.
P(X > 110 customers) = 0.14714
P(X > 120 customers) = 0.02267
P(X > 130 customers) = 0.00171
3) Number of Website Visitors per Hour

For example, suppose a given website


receives an average of 20 visitors per
hour.

P(X > 25 visitors) = 0.11218


P(X > 30 visitors) = 0.01347
P(X > 35 visitors) = 0.00080
4) Number of Bankruptcies Filed per Month

For example, suppose a given bank has


an average of 3 bankruptcies filed by
customers each month.
P(X = 0 bankruptcies) = 0.04979
P(X = 1 bankruptcy) = 0.14936
P(X = 2 bankruptcies) = 0.22404
5) Number of Network Failures per Week

For example, suppose a given company


experiences an average of 1 network
failure per week.
P(X = 0 failures) = 0.36788
P(X = 1 failure) = 0.36788
P(X = 2 failures) = 0.18394
CONCLUSION

To summarize, a Poisson Distribution gives the probability of a number of events in an


interval generated by a Poisson process. The Poisson distribution is defined by the rate
parameter, λ, which is the expected number of events in the interval (events/interval *
interval length) and the highest probability number of events. We can also use the Poisson
Distribution to find the waiting time between events. Even if we arrive at a random time,
the average waiting time will always be the average time between events.

You might also like