Scribd
Upload
3 views

The Poisson Distribution

The Poisson distribution describes the probability of isolated events occurring randomly in time or space, particularly when the number of trials is infinite and the probability of success is very small. It is applicable in scenarios where only the number of occurrences is counted, such as accidents or phone calls, and is characterized by certain conditions related to independence and average rates. Key examples and formulas illustrate its use in calculating probabilities for various events.

Uploaded by

namanverma1402
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
3 views

The Poisson Distribution

The Poisson distribution describes the probability of isolated events occurring randomly in time or space, particularly when the number of trials is infinite and the probability of success is very small. It is applicable in scenarios where only the number of occurrences is counted, such as accidents or phone calls, and is characterized by certain conditions related to independence and average rates. Key examples and formulas illustrate its use in calculating probabilities for various events.

Uploaded by

namanverma1402
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 20

The Poisson Distribution

Key Fact
Binomial distribution is applicable in the cases where we count the number of
successes in n trials. In such cases we know,

a) The number of times the event did occur (i.e., success frequency)
b) The number of times it did not occur (i.e., failure frequency)

In these situations both the success and failure frequency are known.
Table

In the above example, for each sample we can identify number of trials, number of success
and number of failure. For each instance of random variable frequency of success as well as
frequency of failure is known.
Experiment : A unit of space (or time) is divided into a large number of
subdivisions and each subdivision can be considered as a trial, where an event
may or may not occur.
Case
The number of trials becomes infinite but the number of occurrences of the
event in a given unit of space (or time) remains the same.
Results
The probability of success p (as in a binomial distribution) in a single trial
becomes very small.

This is a limiting case of the binomial distribution for large n and very small p
with finite value of np, also called as Poisson Distribution.
Definition
Poisson Distribution

Poisson distribution is used to describe the probability distribution of the


isolated evens which occur at random points in time or space.

Poisson Distribution is used in the situation in which we can count the number of times an
event occurs but it is meaningless to ask for how many times it did not occur.
Examples
1. The number of accident cases reported daily at the emergency
counter.

2. The number of telephone calls received per hour.

3. The number of defects in fabric.

4. The number of organisms seen within one square unit under the
microscope.
Definition
Poisson Discrete Random Variable
A random variable, X, is said to follow the Poisson probability distribution if the
following conditions are satisfied:
1. The number of occurrences of the event in two disjoint intervals are in-
dependent.
2. The probability of an occurrence of the event in a small interval h (where h
is infinitesimally small) is approximately mh, where m is the average rate
at which the event occurs per unit of time or space.
3. The probability of two or more occurrences of the event in a very small
interval, h, is negligible in comparison with the probability of one
occurrence during this small interval.
Formula
Key Fact
The Poisson distribution may be used for counting the number of events which
occur over time or space when:

a) The average (or expected) number of occurrences of the event per unit of
time or space remains the same for some longer period of time or large
amount of space.

b) The number of times an event occurs in one part of time or space does not
affect what happens in another part of time or space.
Table
Partial probability distribution of the random variable X, the number of patients arriving at the emergency
room between 6:00 P.M. and 7:00 P.M—has a Poisson distribution with parameter λ = 6.9.

Insert Table 5.16 from page 242 in Chapter 5.


Figure
Partial probability histogram for the random variable X, the number of patients arriving at the emergency
room between 6:00 P.M. and 7:00 P.M.
Example 1
Defects in yarn manufactured by a local textile mill can be approximated by a
Poisson distribution with a mean of 1.2 defects for every 6 metres of length. If
lengths of 6 metres are to be inspected, find the probability of less than 2 defects.

Solution:
Given m = 1.2. Therefore required probability is
P(X<2) = P(0) + P(1) = 0.663
Table
Cumulative Poisson Probabilities
Example 2
If the number of telephone calls that an operator receives in a half-an hour interval
follows a Poisson probability distribution with an average of 3 calls. What is the
probability that the operator will be idle in a half-an-hour interval? What is the
probability of less than four calls? What is the most likely number of calls that the
operator will receive?

Solution:
We are given m= 3. Therefore, the probability that the operator will be idle during a
half-an-hour interval is given by

P(X=0) = P(0) = 0.05


The probability of less than four calls is given by

P(X<4) = P(X≤3) = 0.647

The most likely number of calls received by the operator is the mode. From Poisson
probability Table, for m = 3, we find that P (2) = P (3) = 0.224. Thus, the two most
frequently occurring values of X are 2 and 3.
Relationship between P(x) and P(x+1)
In Poisson probability distribution, we have

𝑒 −𝑚 𝑚 𝑥
𝑃(𝑥) = 𝑃[𝑋 = 𝑥] =
𝑥!
and
𝑒 −𝑚 𝑚 𝑥 +1
𝑃(𝑥 + 1) = 𝑃[𝑋 = 𝑥 + 1] = 𝑥+1 !
𝑒 −𝑚 𝑚 𝑥 𝑚
=
𝑥! 𝑥 +1

𝑚
=𝑃 𝑥 𝑥 +1
Formula
Procedure
Example 3
Trucks arrive at a dockyard at a mean rate of two per hour. Using the Poisson
approximation, determine the following probabilities for a 30-minute period: (i) no
trucks arrive and (ii) two trucks arrive.

Solution:
As the probabilities have to be calculated for a 30-minute period, the mean of the
Poisson distribution would be
m=1 per half an hour

From the Poisson distribution table, we get

P(X=0) = 0.368 and P(X=2) = 0.184


Thus, the probability of no arrival of a truck in a half an hour period is 0.368 and
that two trucks arrive during this period is 0.184.
Examples

You might also like