GCE A Level The Poisson Distribution

GCE A Level Maths 9709

SMIYL
March 2023

6.1 The Poisson Distribution

In this topic we will learn how to:
• use formulae to calculate probabilities for the distribution P o(λ)

• use the fact that if X ∼ P o(λ) then the mean and variance of X are each
equal to λ
• understand the relevance of the Poisson distribution to the distribution of
random events, and use the Poisson distribution as a model
• use the Poisson distribution as an approximation to the binomial distri-

bution where appropriate
• use the normal distribution, with continuity correction, as an approxima-
tion to the Poisson distribution where appropriate
The Poisson Distribution
The Poisson Distribution is discrete. This means it only takes exact

values e.g 1,2,3,4. It is used to measure the number of events that
occur in a given space or time. For the Poisson Distribution to be
defined four conditions must be met:
• Events must occur at random
• Events must occur singly

• Events must occur at a constant average rate
• Events must occur independently
The notation for defining a Poisson distribution is as follows,
X ∼ P o(λ)
1
Where X is the random variable, P o represents the Poisson Distribu-
tion, λ pronounced ’lambda’ represents the mean or constant average
rate.
Note: Mean and variance are the same when a Poisson distribution
is defined. The symbol to denote mean or variance under a Poisson
distribution is λ.
Calculating Poisson Probabilities
We can use the Poisson distribution to calculate probabilities. The

formula to do this is:
λr
P (X = r) = e−λ ×
r!
where r is the number of events that have occurred in a given space

or time and λ is the mean or constant average rate.
Poisson Approximation to the Binomial Distribution
The Poisson distribution can be used as an approximation to the

binomial distribution. This can be done to simplify calculations, as
calculations can get very complicated under the binomial distribution
as n increases. To do this certain conditions have to be met:
n > 50 and np < 5
Note: Some literature may put the condition p < 0.1 in place of np < 5.
This is an acceptable alternative.
If,
X ∼ B(n, p)
And n > 50 and np < 5, then,
X ∼ P o(np)
Note: Remember that under the binomial distribution, mean is equal

to np, therefore, when we approximate to the Poisson distribution,
λ will be equal to np. Both the binomial distribution and Poisson
distribution are discrete, so there is no need for continuity correction.
Normal Approximation to the Binomial Distribution
2
We can also use the Normal distribution to approximate to the Pois-
son distribution. However, since the Poisson distribution is discrete
and the normal distribution is continuous, we have to do continuity
correction. The conditions for using a normal approximation to the
Poisson distribution are:
λ > 15
If,
X ∼ P o(λ)
And λ > 15, then,

X ∼ N (λ, λ)
Note: Remember that mean and variance are the same under a Pois-
son Distribution, therefore, when we approximate to the normal dis-
tribution, mean and variance will both be equal to λ.
Let’s look at the following examples of the Poisson distribution.

1. The number of eagles seen per hour in a certain location has the distri-
bution Po(1.8). Find the probability that, in a randomly chosen hour, at
least two eagles are seen. (9709/72/F/M/19)
The first step is to define our random variable.
X − r.v, number of eagles seen per hour in a certain location.
X ∼ P o(1.8)
The question wants us to find the probability that, in a ran-

domly chosen hour, at least two eagles are seen. Let’s write that
mathematically,
P (X ≥ 2)
We can write this as:
P (X ≥ 2) = 1 − P (X < 2)
We have to find P (X < 2)
1 − P (X < 2)
Let’s rewrite P (X < 2). Since the Poisson distribution is discrete,
P (X < 2) = P (X = 1) + P (X + 0)
3
Solve for P (X = 1) + P (X + 0) using the formula for calculating
Poisson probabilities.
λr
P (X = r) = e−λ ×
r!
1.81
P (X = 1) = e−1.8 ×
1!
P (X = 1) = 1.8e−1.8
1.80
P (X = 0) = e−1.8 ×
0!
P (X = 0) = e−1.8
Add them together,
P (X < 2) = 1.8e−1.8 + e−1.8
Simplify,
P (X < 2) = 2.8e−1.8
Substitute P (X < 2) into our original equation,
P (X ≥ 2) = 1 − P (X < 2)
P (X ≥ 2) = 1 − (2.8e−1.8 )
P (X ≥ 2) = 0.537163113
Therefore the final answer is,
P (X ≥ 2) = 0.537
2. The random variable X has the distribution P o(115). Use a suitable ap-
proximating distribution to find P (X ≤ 110). (9709/71/M/J/19 number
5)
X ∼ P o(115)
We have to inspect λ to know which approximation this is,
λ = 115 > 15
Use normal approximation to the Poisson distribution.
4
Since λ is both mean and variance when we move to the normal
distribution,
X ∼ N (λ, λ)
X ∼ N (115, 115)
Since we’re moving from a discrete distribution to a continuous

distribution we have to do continuity correction,
P (X ≤ 110) −→ P (X < 110.5)
Solve P (X < 110.5) using a normal distribution.
P (X < 110.5)

110.5 − 115
P Z< √
115
P (Z < −0.420)
1 − ϕ(0.420)
1 − 0.663
0.337
Therefore, the final answer is,
0.337
3. The random variable X has the distribution B(300, 0.01). Use a Poisson
approximation to find P (2 < X < 6). (9709/73/O/N/19 number 5)
X ∼ B(300, 0.01)
We are instructed to use a Poisson approximation,
X ∼ P o(np)
Note: In some cases the question may not explicitly instruct

you to use a Poisson distribution, check if the conditions for a
Poisson approximation to the binomial distribution are satisfied.
If they are, then that is the suitable approximation.
Let’s find np,

np = 300 × 0.01
np = 3
5
Therefore,
X ∼ P o(3)
Let’s use the Poisson distribution to evaluate P (2 < X < 6),
P (2 < X < 6) = P (X = 3, 4, 5)
Note: Since both the Poisson and binomial distribution are dis-
crete there is no need for continuity correction.
3
34 35

−3 3
P (X = 3, 4, 5) = e + +
3! 4! 5!
P (X = 3, 4, 5) = 0.4928919768
P (X = 3, 4, 5) = 0.493
Therefore, the final answer is,
P (2 < X < 6) = 0.493

GCE A Level The Poisson Distribution

Uploaded by

Copyright:

Available Formats

GCE A Level The Poisson Distribution

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

GCE A Level The Poisson Distribution

Uploaded by

Copyright:

Available Formats

GCE A Level Maths 9709

6.1 The Poisson Distribution

• use formulae to calculate probabilities for the distribution P o(λ)

• use the Poisson distribution as an approximation to the binomial distri-

The Poisson Distribution

The Poisson Distribution is discrete. This means it only takes exact

• Events must occur singly

The notation for defining a Poisson distribution is as follows,

Calculating Poisson Probabilities

We can use the Poisson distribution to calculate probabilities. The

where r is the number of events that have occurred in a given space

Poisson Approximation to the Binomial Distribution

The Poisson distribution can be used as an approximation to the

n > 50 and np < 5

And n > 50 and np < 5, then,

Note: Remember that under the binomial distribution, mean is equal

Normal Approximation to the Binomial Distribution

And λ > 15, then,

Let’s look at the following examples of the Poisson distribution.

The first step is to define our random variable.

X − r.v, number of eagles seen per hour in a certain location.

The question wants us to find the probability that, in a ran-

We can write this as:

We have to find P (X < 2)

Let’s rewrite P (X < 2). Since the Poisson distribution is discrete,

Add them together,

P (X < 2) = 1.8e−1.8 + e−1.8

Substitute P (X < 2) into our original equation,

Therefore the final answer is,

We have to inspect λ to know which approximation this is,

Use normal approximation to the Poisson distribution.

Since we’re moving from a discrete distribution to a continuous

P (X ≤ 110) −→ P (X < 110.5)

Solve P (X < 110.5) using a normal distribution.

Therefore, the final answer is,

We are instructed to use a Poisson approximation,

Note: In some cases the question may not explicitly instruct

Let’s find np,

Let’s use the Poisson distribution to evaluate P (2 < X < 6),

Therefore, the final answer is,

P (2 < X < 6) = 0.493

You might also like