The Poisson Processes

1. The Poisson distribution is a discrete distribution that is used for counts that do
not have a natural upper bound.

For example: The number of defects on a new car

The number of arrivals at a traffic light or any other place
The number of hurricanes off the coast of Florida during a year
The number of visits to a website (Facebook, Google)

A Poisson distribution is completely determined with just one parameter, its mean
denoted by .

The probability distribution function is given by

λ x e− λ
f(x; ) =
x!

Example The number of admissions per day at an emergency room has a Poisson
distribution with mean 5. Find the probability of

a) exactly 2 admissions
b) at most 2 admissions

52 e−5
Solution a) f(2,5) = = .084
2!

b) f(0,5) + f(1,5) + f(2,5) = .125

2. The Poisson can be used to approximate the binomial distribution.

We can use  = np.

Example It is known that 5% of the books bound at a certain bindery have

defective bindings. Find the probability that 2 out of 100 books will have defective
bindings using
a) The binomial distribution
b) The Poisson approximation

Solution a) b(2,100,.05) =
= .081

b) First find  = np = 100(.05) = 5.

52 e−5
f(2,5) = = .084
2!

3. For a Poisson distribution  =  and 2 = .

Example Over a 10-minute period, a counter records an average of 1.3 gamma

particles per millisecond coming from a radioactive substance. It has been
determined that if X is the number of gamma particles during the next millisecond,
then X is approximated by a Poisson distribution. Determine

a) The probability of one or more gamma particles

b) The variance

Solution a) First note that  = 1.3.

We want P(X  1). We can use the complement 1 – P(X = 0).

λ x e− λ 1.30 e−1.3
P(X = 0) = f(0; 1.3) = = = e–1.3
x! 0!

So P(X  1) = 1– e–1.3 = .727

b) 2 = 1.3
4. A Poisson process, named after the French mathematician Siméon-Denis
Poisson (1781–1840), is a random process in which events occur continuously and
independently of one another.

Examples that are well-modeled as Poisson processes include:

The radioactive decay of atoms

Telephone calls arriving at a switchboard

Example If a bank receives on the average 6 bad checks per day, what are the
probabilities that it will receive

a) 4 bad checks on a given day?

b) 10 bad checks over any 2 consecutive days?

5. The geometric distribution

Recall the example where we were interested in the number of cars that must be
inspected until one is found to fail the nitrogen oxide emission standard.

If p is the probability that a car fails, then 1 − p is the probability of passing.

The probability that x cars must be checked until a failure is encountered is given
by p(1 − p)x-1.

This probability distribution is called the geometric distribution and has the
probability function g(x;p) = p(1 − p)x-1.

1
The mean for this distribution is given by μ= p .

Example If the probability is 0.05 that a certain kind of measuring device will
show excessive drift, what is the probability that
a) The sixth measuring device tested will be the first to show excessive drift?
b) The fifth measuring device tested will be the first to show excessive drift?

Example You're playing Heads and Tails. You decide to play until the first
Head turns up, and then stop the game.
a) If the coin is fair, what is the probability that the first heads turns up on the
fourth flip?
b) If the probability of a heads is .4, what is the probability that the first heads
turns up on the fourth flip?
6. The negative binomial distribution

A negative binomial experiment is a statistical experiment that has the following

properties:

 The experiment consists of x repeated trials.

 Each trial can result in just two possible outcomes. We call one of these
outcomes a success and the other, a failure.
 The probability of success, denoted by p, is the same on every trial.
 The trials are independent; that is, the outcome on one trial does not affect
the outcome on other trials.
 The experiment continues until r successes are observed, where r is
specified in advance.

Example You flip a coin repeatedly and count the number of times the coin lands
on heads. You continue flipping the coin until it has landed 5 times on heads.

The negative binomial distribution gives the number of Bernoulli trials X to obtain
a specified number of r successes.

x−1 r x−r
( )
f(x) = r −1 p (1− p) for x = r, r+1,…

Example Bob is a high school basketball player. He is a 70% free throw shooter.
That means his probability of making a free throw is 0.70. During the season, what
is the probability that Bob makes his third free throw on his fifth shot?

Solution: This is an example of a negative binomial experiment. The probability of

success (p) is 0.70, the number of trials (x) is 5, and the number of successes (r) is
3.
To solve this problem, we enter these values into the negative binomial formula.

f(5) = 4C2 * 0.73 * 0.32 = 6 * 0.343 * 0.09 = 0.18522

Thus, the probability that Bob will make his third successful free throw on his fifth
shot is 0.18522.

Example 2

Let's reconsider the above problem from Example 1. This time, we'll ask a slightly
different question: What is the probability that Bob makes his first free throw on
his fifth shot?

Solution: This is an example of a geometric distribution, which is a special case of

a negative binomial distribution. Therefore, this problem can be solved using the
negative binomial formula or the geometric formula.

The probability of success (p) is 0.70, the number of trials (x) is 5, and the number
of successes (r) is 1. We enter these values into the negative binomial formula.

f(5) = 4C0 * 0.71 * 0.34 = 0.00567

Now, we demonstrate a solution based on the geometric formula.

g(5; 0.7) = 0.7 * 0.34 = 0.00567

7. The multinomial distribution

The multinomial distribution is a generalization of the binomial distribution which

arises when each trial has more than two possible outcomes.

For example:
A manufactured product is classified as superior, average or poor
A four-sided die is tossed and the outcomes are 1, 2, 3 and 4
An experiment is judged as successful, unsuccessful or inconclusive

Suppose we are interested in: getting x1 outcomes of the first kind,

getting x2 outcomes of the second kind,
…
getting xk outcomes of the k’th kind,

where the outcomes on each trial are mutually exclusive and have probabilities of
k k

p1, p2, …, pk of occurring with ∑ pi = 1 and ∑ x i = n.

i=1 i=1

n! x x x
Then the probability function is given by f(x1,x2,…,xk) = x ! x ! … x ! p1 p2 … p k
1 2 k

1 2 k

Example 1

Suppose a card is drawn randomly from an ordinary deck of playing cards, and
then put back in the deck. This exercise is repeated five times. What is the
probability of drawing 1 spade, 1 heart, 1 diamond, and 2 clubs?

Solution: To solve this problem, we apply the multinomial formula. We know the
following:

 The experiment consists of 5 trials, so n = 5.

 The 5 trials produce 1 spade, 1 heart, 1 diamond, and 2 clubs; so n1 = 1, n2 =
1, n3 = 1, and n4 = 2.
  On any particular trial, the probability of drawing a spade, heart, diamond,
or club is 0.25, 0.25, 0.25, and 0.25, respectively. Thus, p1 = 0.25, p2 = 0.25,
p3 = 0.25, and p4 = 0.25.

We plug these inputs into the multinomial formula, as shown below:

f(1,1,1,2) = [ n! / ( n1! * n2! * ... nk! ) ] * ( p1n1 * p2n2 * . . . * pknk )

= [ 5! / ( 1! * 1! * 1! * 2! ) ] * [ (0.25)1 * (0.25)1 * (0.25)1 * (0.25)2 ]

= 0.05859

Thus, if we draw five cards with replacement from an ordinary deck of playing
cards, the probability of drawing 1 spade, 1 heart, 1 diamond, and 2 clubs is
0.05859.

Example 2

Suppose we have a bowl with 10 marbles - 2 red marbles, 3 green marbles, and 5
blue marbles. We randomly select 4 marbles from the bowl, with replacement.
What is the probability of selecting 2 green marbles and 2 blue marbles?

Solution: To solve this problem, we apply the multinomial formula. We know the
following:

 The experiment consists of 4 trials, so n = 4.

 The 4 trials produce 0 red marbles, 2 green marbles, and 2 blue marbles; so
nred = 0, ngreen = 2, and nblue = 2.
 On any particular trial, the probability of drawing a red, green, or blue
marble is 0.2, 0.3, and 0.5, respectively. Thus, pred = 0.2, pgreen = 0.3, and pblue
= 0.5

We plug these inputs into the multinomial formula, as shown below:

f(0,2,2) = [ n! / ( n1! * n2! * ... nk! ) ] * ( p1n1 * p2n2 * . . . * pknk )
= [ 4! / ( 0! * 2! * 2! ) ] * [ (0.2)0 * (0.3)2 * (0.5)2 ]
= 0.135

Thus, if we draw 4 marbles with replacement from the bowl, the probability of
drawing 0 red marbles, 2 green marbles, and 2 blue marbles is 0.135.