Scribd
Upload
135 views4 pages

Poisson Distribution Essay

Poisson distribution is used to model the number of events that occur randomly in a fixed interval of time or space. It has one parameter λ which represents the average number of occurrences. The distribution applies when events are independent and the probability of an event is very small. Common applications include modeling network failures, customer arrivals, and broken items in manufacturing. The binomial distribution can be approximated by the Poisson distribution when the number of trials is large and the probability of success is small.

Uploaded by

Siti Rania Norazli Sham
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
135 views4 pages

Poisson Distribution Essay

Poisson distribution is used to model the number of events that occur randomly in a fixed interval of time or space. It has one parameter λ which represents the average number of occurrences. The distribution applies when events are independent and the probability of an event is very small. Common applications include modeling network failures, customer arrivals, and broken items in manufacturing. The binomial distribution can be approximated by the Poisson distribution when the number of trials is large and the probability of success is small.

Uploaded by

Siti Rania Norazli Sham
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

POISSON DISTRIBUTION

DATE :24/11/2022

NAME OF INSTRUCTOR:
Assoc. Prof Dr. Mohammad Mustafizur Rahman

PREPARED BY:
2213054
Background of Poisson Distribution

The Poisson Distribution was developed in 1830 by a French mathematician,


Siméon Denis Poisson and was originally applied to the world of gambling to show
the spread of the probable number of times that a gambler would win at a gambling
game within a large number of times that the game was played. However, the
gambler paid no attention to Poisson’s prediction.

During World War II, there was a British statistician who used Poisson
Distribution to analyze bomb hits in the city of London. R.D. Clarke has refined the
Poisson Distribution as a statistical model and worked to reassure the British
government that the German bombs fell randomly, or purely by chance, and that the
enemies were lacking of sufficient information to be targeting certain areas of the
city. Ever since then, the wide range of possible applications of Poisson’s statistical
tool became evident.

Poisson Distribution falls under discrete probability distribution, which means


that it gives the probability of a discrete or countable outcome. The discrete outcome
provided by Poisson Distribution is the probability of an event occuring at a certain
number of times within a given time or space interval which is represented by the
letter k. The Poisson distribution has only one parameter, λ (lambda), which is the
mean number of events.

This distribution occurs when there are events that do not occur as the
outcomes of a definite number of outcomes. Poisson distribution is used under three
conditions. First, the number of trials “n” tends to infinity. Secondly, the probability of
success “p” tends to zero. Thirdly, np = 1 is finite.

The Poisson distribution is used to estimate the probability of an event


occurring within a certain time.

Assumption of Poisson Distribution

Poisson Distribution is only suitable to be used if all four of its assumptions


are met. The number of the events that may occur within an interval of time must be
countable and can take on the values of 0, 1, 2, 3 and so on. Next, we assume that
the occurrence of one event will not have an effect on the probability that another
event will occur, which means that the occurrence of events are independent. The
third assumption is that we must be able to calculate the average rate at which the
event occurs. Not only that the average rate at which events occur during a given
time interval must be able to be calculated, it is also assumed that the rate is
constant over each sub-interval. The last assumption is that two events cannot occur
at exactly the same time. We assume that at each extremely small sub-interval,
exactly one event occurs or does not occur.
Application of Poisson Distribution

The application of Poisson distribution can be applied on many situations. For


instance, it can be used to explain number of local cases of Covid-19 per week, it
can also be used to explain the number of meteor strikes per year. Also, it can be
used to describe the number of fish sold per day and to describe the number of
customers walked into a high-end store each month. Moreover, it can be used to
explain the number of scarfs sold by a store per day. The number of sprays of
perfume used by an individual per day and the number of car that drives through a
street can also be explained by using Poisson distribution.

One of the application is number of network failures per week. Poisson


distribution is used by cell phone companies and wireless service providers to
improve the efficiency of the service and the customer satisfaction ratio. With the
history of the number of network failures occurring in the locality at a particular time
and duration is well known, the probability of a certain number of network failures
that will be occurring in the future can be determined easily with Poisson distribution.
This helps the broadcasting organisations be prepared for the problems that might
occur and draft the solution in advance, so that the customers accessing their
services don’t have to suffer the inconvenience.

For instance, the Poisson distribution is appropriate for modeling the number
of network failures per week, if they know that the average 120 network failures per
week. Although the average is 120 network failures, they could theoretically get any
number of network failures during that time period. The events are effectively
independent since there is no reason to expect a network failure to affect the
chances of another network failure. The occurrence rate may be assumed to be
constant. It is reasonable to assume that the probability of getting a network failure
report in the first half week is the same as the probability of getting a network failure
report in the final half week.

For example, an average of 0.61 number of network failure per week is recorded.
You want to calculate the probability that exactly two network failure recorded in a
day, assuming that the number of horse kick deaths per week follows a Poisson
distribution. To calculate :

r = 2 network failures
λ = 0.61 number of network failure per week
e = 2.718

P(X = r) = e-λ λr / r!
P(X = 2) = (2.718-0.61)(0.612) / 2!
P(X = 2) = (0.54339)(0.3721) / 2
P(X = 2) = 0.101
The probability that exactly two number of network failure in a day of the week is
0.101.
Poisson approximation with examples

For those situations in which n is large and p is very small, the Poisson
distribution can be used to approximate the binomial distribution. If n > 20 and np < 5
OR nq < 5 then the Poisson is a good approximation.The value of the mean needed
for the Poisson approximation is λ = np. Poisson approximation can be used to
approximate the number of restaurant visitors per hour and number of emergency
calls received by hospital per week. Moreover, it can be used to approximate the
number of absentees at an exam. It can also approximate the number of meals sold
by a restaurant per day, and number of books sold at a book fair per day.

As an example, a factory puts biscuits into boxes of 100. The probability that a
biscuit is broken is 0.03. Find the probability that a box contains 2 broken biscuits.
This is a binomial distribution with n = 100 and p = 0.03. Using the Poisson
approximation (test: np = 100 x 0.3 = 3, which is less than 5). Let X be the random
variable of the number of broken biscuits. The mean λ = np = 100 × 0.3 = 3. From
the table, we get that P(X = 2) = 0.224. So the probability that a box contains two
broken biscuits is 0.224.

Relation between Binomial and Poisson distributions

The Poisson distribution is actually a limiting case of a Binomial distribution


when the number of trials, n, gets very large and p, the probability of success, is
small. As we know, if n≥100 and np≤10, the Poisson distribution can provide a very
good approximation to the binomial distribution. This is particularly useful as
calculating the combinations inherent in the probability formula associated with the
binomial distribution can become difficult when n is large. To better see the
connection between these two distributions, consider the binomial probability of
seeing r successes in n trials, with the aforementioned probability of success, p,
P(r)=nCrprqn-r. Let us denote the expected value of the binomial distribution, np, by λ.
Hence, this means that p=λ/n. Since q=1−p, so q=1− λ/n. If we use this to rewrite
P(r) in terms of λ, n, and r, we obtain P(r)= nCr(λ/n)r(1− λ/n)n-r. Using the standard
formula for the combinations of n things taken x at a time and some simple
properties of exponents, we can further expand things to
P(r) = ((n(n−1)(n−2)⋯(n−x+1)) / r!) ⋅ (λr/nr)(1− λn)n-r. Notice that there are exactly r
factors in the numerator of the first fraction. Let us swap denominators between the
first and second fractions, splitting the nr across all of the factors of the first fraction's
numerator. Hence, P(r) = (n/n) ⋅ ((n−1)/n)⋯((n−r+1)/n) ⋅ (λr/r!)n (1− (λ/n))-r. It should
now be relatively easy to see that if we took the limit as n approaches infinity,
keeping x and λ fixed, the first x fractions in this expression would tend towards 1, as
would the last factor in the expression. The second to last factor, as was mentioned
before, tends towards e−λ, and the remaining factor stays unchanged as it does not
depend on n. As such, lim n→∞ P(r) = e −λλr / r!.

You might also like