Some Discrete Probability Distributions - Part II

Week – 6
MKT3802 Statistical and Experimental Methods for Engineers

March 27, 2024

Outline

Hypergeometric distribution
Multivariate Hypergeometric Distribution
Poisson Distribution

Some Discrete Probability Distributions - Part

March
II 27, 2024 2 / 25
Hypergeometric distribution

Similar types of applications

Distinction between Binomial Distribution is the way the sampling
is done
Interested in computing probability for the # observations fall into
a particular category
In contrast to binomial one, independence among trials is not
required
Uses:
Acceptance sampling (i.e. lot acceptance)
Electronic testing
Quality assurance

Some Discrete Probability Distributions - Part

March
II 27, 2024 3 / 25
Hypergeometric distribution

Example: Sampling from a deck of cards

For Binomial Distribution
the sampling must be done with replacement
e.g. independent trials
For Hypergeometric Distribution
the sampling must be done without replacement
e.g. dependent trials

Some Discrete Probability Distributions - Part

March
II 27, 2024 4 / 25
Hypergeometric distribution

In general, we are interested in the probability of selecting x

successes from the k items labeled successes and n − x failures
from the N − k items labeled failures when a random sample of
size n is selected from N items.
Has the following two properties:
1 A random sample of size n is selected without replacement from N
items.
2 Of the N items, k may be classified as successes and N − k are
classified as failures.

Some Discrete Probability Distributions - Part

March
II 27, 2024 5 / 25
Hypergeometric Distribution

Example (1)
A particular part that is used as an injection device is sold in lots of
10. The producer deems a lot acceptable if no more than one defective
is in the lot. A sampling plan involves random sampling and testing 3
of the parts out of 10. If none of the 3 is defective, the lot is accepted.
Comment on the utility of this plan.

Some Discrete Probability Distributions - Part

March
II 27, 2024 6 / 25
Hypergeometric distribution

Definition
The probability distribution of the hypergeometric random variable X,
the number of successes in a random sample of size n selected from N
items of which k are labeled success and N − k labeled failure, is
! !
k N −k
x n−x
h(x; N, n, k) = !
N
n

where
max {0, n − (N − k)} ≤ x ≤ min {n, k}

Some Discrete Probability Distributions - Part

March
II 27, 2024 7 / 25
Hypergeometric Distribution

Example (2)
Lots of 40 components each are deemed unacceptable if they contain 3
or more defectives. The procedure for sampling a lot is to select 5
components at random and to reject the lot if a defective is found.
What is the probability that exactly 1 defective is found in the sample
if there are 3 defectives in the entire lot?

Some Discrete Probability Distributions - Part

March
II 27, 2024 8 / 25
Hypergeometric Distribution

Expected value, the mean, and the variance

The mean and variance of the hypergeometric distribution h(x; N, n, k)
are
nk
µ=
N
 
2 (N − n) k k
σ = n 1−
(N − 1) N N

Example (3)
Find the mean and variance of the random variable of Example 2 and
then use Chebyshev’s theorem to interpret the interval µ ± 2σ

Some Discrete Probability Distributions - Part

March
II 27, 2024 9 / 25
Relationship to the Binomial Distribution

if n is small compared to N
binomial distribution can be used to approximate hypergeometric
distribution
rule of thumb: n
N ≤ 0.05
p in binomial distribution may be approximated by Nk
k
µ = np vs. µ = n
N
 
2 2 (N − n) k k
σ = npq vs. σ = n 1−
(N − 1) N N

Some Discrete Probability Distributions - Part

March
II 27, 2024 10 / 25
Hypergeometric Distribution

Example (4)
A manufacturer of automobile tires reports that among a shipment of
5000 sent to a local distributor, 1000 are slightly blemished. If one
purchases 10 of these tires at random from the distributor, what is the
probability that exactly 3 are blemished?

Some Discrete Probability Distributions - Part

March
II 27, 2024 11 / 25
Hypergeometric Distribution

n/N = 10/5000 ≤ 0.05 n/N = 10/50 ≥ 0.05

0.35 0.35
Binomial Binomial
hypergeometric hypergeometric
0.3 0.3

0.25 0.25

0.2 0.2
P(x)

P(x)
0.15 0.15

0.1 0.1

0.05 0.05

0 0
0 1 2 3 4 5 6 7 8 9 10 0 1 2 3 4 5 6 7 8 9 10
X X

Some Discrete Probability Distributions - Part

March
II 27, 2024 12 / 25
Multivariate Hypergeometric Distribution

Definition
If N items can be partitioned into the k cells A1 , A2 , ..., Ak with
a1 , a2 , ..., ak elements, respectively, then the probability distribution of
the random variables X1 , X2 , ..., Xk , representing the number of
elements selected from A1 , A2 , ..., Ak in a random sample of size n, is
! ! !
a1 a2 ak
...
x1 x2 xk
f (x1 , x2 , ..., xk ; a1 , a2 , ...ak , N, n) = !
N
n

with
k
X k
X
xi = n and ai = N
i=1 i=1

Some Discrete Probability Distributions - Part

March
II 27, 2024 13 / 25
Multivariate Hypergeometric Distribution

Example (5)
A group of 10 individuals is used for a biological case study. The group
contains 3 people with blood type O, 4 with blood type A, and 3 with
blood type B. What is the probability that a random sample of 5 will
contain 1 person with blood type O, 2 people with blood type A, and 2
people with blood type B?

Some Discrete Probability Distributions - Part

March
II 27, 2024 14 / 25
Poisson Distribution

Definition
Experiments yielding numerical values of a random variable X, the
number of outcomes occurring during a given time interval or in a
specified region, are called Poisson experiments.

X may be: number of

telephone calls received per hour
days school is closed during the winter
games postponed due to rain during a season
mice per acre
bacteria in a given culture
typing errors on a page
...

Some Discrete Probability Distributions - Part

March
II 27, 2024 15 / 25
Properties of the Poisson Process

1 The number of outcomes occurring in one time interval (or

specified region of space) is independent of the number that occur
in any other disjoint time interval (or region)
2 The probability that a single outcome will occur during a very
short time interval (or in a small region) is
1 proportional to the length of the time interval (or the size of the
region)
2 does not depend on the number of outcomes occurring outside this
time interval (or region)
3 The probability that more than one outcome will occur in such a
short time interval (or fall in such a small region) is negligible.

Some Discrete Probability Distributions - Part

March
II 27, 2024 16 / 25
Poisson Distribution1

Definition (Poisson Distribution)

The probability distribution of the Poisson random variable X,
representing the number of outcomes occurring in a given time interval
or specified region denoted by t, is

e−λt (λt)x
p (x; λt) =
x!
For calculating Poisson probability sums, similar to binomial sums, a
Table exist for selected values of λt ranging from 0.1 to 18.0.
r
X
P (r; λt) = p (x; λt)
x=0

1
The derivation of the formula for p(x; λt), based on the properties of a Poisson
process listed in the previous slide, is beyond the scope of this course
Some Discrete Probability Distributions - Part
March
II 27, 2024 17 / 25
Poisson Distribution

Some Discrete Probability Distributions - Part

March
II 27, 2024 18 / 25
Poisson Distribution

Example (6)
During a laboratory experiment, the average number of radioactive
particles passing through a counter in 1 millisecond is 4. What is the
probability that 6 particles enter the counter in a given millisecond?

Example (7)
Ten is the average number of oil tankers arriving each day at a certain
port. The facilities at the port can handle at most 15 tankers per day.
What is the probability that on a given day tankers have to be turned
away?

Some Discrete Probability Distributions - Part

March
II 27, 2024 19 / 25
Poisson Distribution
Nature of the Poisson Probability Function

Theorem
Both the mean and the variance of the Poisson distribution p(x; λt) are
equal to λt.

µ = λt σ 2 = λt
Some Discrete Probability Distributions - Part
March
II 27, 2024 20 / 25
Approximation of Binomial Distribution by a Poisson
Distribution

For low values of p and large values of n

Poisson distribution can be used with µ = np to approximate
binomial distribution
if p is close to 1, interchange success with failure and use Poisson
distribution

Theorem
Let X be a binomial random variable with probability distribution
b(x; n, p). When n → ∞, p → 0, and np −−−→ µ remains constant,
n→∞

n→∞
b(x; n, p) −−−→ p(x; µ)

Some Discrete Probability Distributions - Part

March
II 27, 2024 21 / 25
Approximation of Binomial Distribution by a Poisson
Distribution

Example (8)
In a certain industrial facility, accidents occur infrequently. It is known
that the probability of an accident on any given day is 0.005 and
accidents are independent of each other.
a What is the probability that in any given period of 400 days there
will be an accident on one day?
b What is the probability that there are at most three days with an
accident?

Some Discrete Probability Distributions - Part

March
II 27, 2024 22 / 25
Approximation of Binomial Distribution by a Poisson
Distribution

p = 0.005 p = 0.1
10 -4
0.3 2
Binomial
Binomial
Poisson 1.8 Poisson
0.25
1.6

1.4
0.2
1.2
P(x)

P(x)
0.15 1

0.8
0.1
0.6

0.4
0.05
0.2

0 0
0 5 10 15 20 10 11 12 13 14 15 16 17 18 19 20
X X

Some Discrete Probability Distributions - Part

March
II 27, 2024 23 / 25
Approximation of Binomial Distribution by a Poisson
Distribution

Example (9)
In a manufacturing process where glass products are made, defects or
bubbles occur, occasionally rendering the piece undesirable for
marketing. It is known that, on average, 1 in every 1000 of these items
produced has one or more bubbles. What is the probability that a
random sample of 8000 will yield fewer than 7 items possessing
bubbles?

Some Discrete Probability Distributions - Part

March
II 27, 2024 24 / 25
End of Lesson

Questions?

Some Discrete Probability Distributions - Part

March
II 27, 2024 25 / 25