MTH305: Probability and Statistics

Chapter 5: Some Discrete Probability

Distributions
Lecture #10

Lebanese American University

Dr. Houssein NASSER EL DINE

Course Plan

Chapters 2 Probability

Chapter 3 Random Variables and Probability Distributions

Chapter 4 Mathematical Expectation

Chapter 5 Some Discrete Probability Distributions

Chapter 6 Some Continuous Probability Distributions

Chapter 8 Sampling Distributions

Chapter 9 One Sample Estimation Problems

Houssein NASSER EL DINE 2 / 40

Table of contents

1 Poisson Distribution

2 Poisson Probability Table

3 Mean and Variance of a Poisson R.V.

4 Exercises

5 Correlation coefficient

6 Chebyshev’s Theorem

7 Geometric Distribution

8 Mean and Variance of a Geometric R.V.

Houssein NASSER EL DINE 3 / 40

 Poisson Distribution

1 Poisson Distribution

2 Poisson Probability Table

3 Mean and Variance of a Poisson R.V.

4 Exercises

5 Correlation coefficient

6 Chebyshev’s Theorem

7 Geometric Distribution

8 Mean and Variance of a Geometric R.V.

Houssein NASSER EL DINE 4 / 40

 Poisson Distribution

Definition
The probability distribution of the Poisson R.V. X , represents the number of outcomes
occurring in a given time interval denoted by t, or specified region, and it is given by:

e −λt (λt)x
f (x) = x = 0, 1, 2, · · · .
x!
where t is the specific time and λ is the average number of outcomes per unit time.

Example
X is number of telephones call per hour received by an office.
X is the number of days school is closed due to snow during the winter.

Notation
A R.V. X which is a Poisson R.V. is denoted by:

X ∼ P(λt)

Houssein NASSER EL DINE 5 / 40

 Poisson Distribution

Example
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?
Solution:
Let X be the number of particles passing through a counter in a given millisecond (t = 1) ,
then
X ∼ P(λt).
Given that the average in 1 millisecond is 4 so λ = 4. Thus,

e −4(1) (4(1))6
P(X = 6) = f (6) = = 0.104.
6!

Houssein NASSER EL DINE 6 / 40

 Poisson Probability Table

1 Poisson Distribution

2 Poisson Probability Table

3 Mean and Variance of a Poisson R.V.

4 Exercises

5 Correlation coefficient

6 Chebyshev’s Theorem

7 Geometric Distribution

8 Mean and Variance of a Geometric R.V.

Houssein NASSER EL DINE 7 / 40

 Poisson Probability Table

Frequently, we are interested in problems where it is necessary to find P(X < r ) or

P(a ≤ X ≤ b).
Fortunately, Poisson sums:
r
X r
X
P(X ≤ r) = F (r) = P(X = x) = P(x, λt)
x=0 x=0

are available in a given organized table for some selected values of λt.
We illustrate the use of this table in the following example.

Houssein NASSER EL DINE 8 / 40

 Poisson Probability Table

Houssein NASSER EL DINE 9 / 40

 Poisson Probability Table

Example
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?
Solution:
Let X be the number of oil tankers arriving in one day (t = 1), then X ∼ P(10). Thus

P(X > 15) = 1 − P(X ≤ 15) = 1 − F (15) = 1 − 0.9513 = 0.0487.

Houssein NASSER EL DINE 10 / 40

 Mean and Variance of a Poisson R.V.

1 Poisson Distribution

2 Poisson Probability Table

3 Mean and Variance of a Poisson R.V.

4 Exercises

5 Correlation coefficient

6 Chebyshev’s Theorem

7 Geometric Distribution

8 Mean and Variance of a Geometric R.V.

Houssein NASSER EL DINE 11 / 40

 Mean and Variance of a Poisson R.V.

Rule
The mean and the variance of the Poisson distribution X ∼ P(λt) are:

µ = σ 2 = λt.

Houssein NASSER EL DINE 12 / 40

 Mean and Variance of a Poisson R.V.

Example
The number of Industrial injuries per working week in a particular factory is known to follow a
Poisson distribution with mean 0.5. Find the probability that:
1 In a particular week there will be (a) less than 2 accidents (b) more than 2 accidents.
2 In a 3 week period, there will be no accidents.
Solution: Let X be the number of accidents in one week (t = 1), so

X ∼ P(0.5)

1 (a) P(X < 2) = P(X ≤ 1) = F (1) = 0.9098 using the table.

(b) P(X > 2) = 1 − P(X ≤ 2) = 1 − F (2) = 1 − 0.9856 = 0.0144 .
2 Let Y be the number of accidents in a 3 week period ⇒ t = 3, so
Y ∼ P(0.5 × 3) = P(1.5)

e −0.5(3) (0.5(3))0 e −0.5(3)

P(Y = 0) = = = 0.223.
0! 1

Houssein NASSER EL DINE 13 / 40

 Mean and Variance of a Poisson R.V.

Houssein NASSER EL DINE 14 / 40

 Exercises

1 Poisson Distribution

2 Poisson Probability Table

3 Mean and Variance of a Poisson R.V.

4 Exercises

5 Correlation coefficient

6 Chebyshev’s Theorem

7 Geometric Distribution

8 Mean and Variance of a Geometric R.V.

Houssein NASSER EL DINE 15 / 40

 Exercises

Exercise 1.
At a particular supermarket, 80 percent of customers have the supermarket club card.
Determine the probability that, in a random sample of 10 customers:
1 Exactly 4 customers have the supermarket club card.
2 At most 2 customers have the supermarket club card.
3 At least 7 customers have the supermarket club card.
Solution:
Let X be the number of customers that have the supermarket club card, then
X ∼ B(n = 10, p = 0.8).

1 P(X = 4) =10C4 (0.8)4 (0.2)6 = 0.005505.

2nd Method: P(X = 4) = F (4) − F (3) = 0.0064 − 0.0009 = 0.0055.
2 P(X ≤ 2) = F (2) = 0.0001.
2nd Method: P(X ≤ 2) = P(X = 2) + P(X = 1) + P(X = 0).
3 P(X ≥ 7) = 1 − P(X < 7) = 1 − P(X ≤ 6) = 1 − F (6) ,
using the table: F (6) = 0.1209 ⇒ P(X ≥ 7) = 1 − 0.1209 = 0.8791. 2nd Method:
P(X ≥ 7) = P(X = 7) + P(X = 8) + P(X = 9) + P(X = 10).

Houssein NASSER EL DINE 16 / 40

 Exercises

Houssein NASSER EL DINE 17 / 40

 Exercises

Exercise 2.
The probability that a student in an elementary school SSßpeaks English fluently is 0.6. A
group of 10 is selected at random from the students of this school. Let X be the number of
students who speak English fluently in this sample.
1 What model you propose for X?
2 What is the probability that 3 students speaks English fluently?
3 What is the probability that at most 7 students speak English fluently?
4 What is the probability that at least 8 students speak English fluently?
Solution:
1 Here we have 10 students, each students either speaks fluently or not, and the
probability of speaking fluently is constant 0.6, so

X ∼ B(n = 10, p = 0.6).

2 We have
P(X = 3) =10C3 (0.6)3 (0.4)7 = 0.042467.
2nd Method : P(X = 3) = F (3) − F (2) .

Houssein NASSER EL DINE 18 / 40

 Exercises

Exercise 2.
Solution:
3 P(X ≤ 7) = F (7) = 0.8327.
2nd Method:
7
X 7
X
10
P(X ≤ 7) = P(X = k ) = Ck (0.6)k (0.4)10−k .
k =0 k =0

4 P(X ≥ 8) = 1 − P(X < 8) = 1 − P(X ≤ 7) = 1 − F (7) ,

using the table:

F (7) = 0.8327 ⇒ P(X ≥ 8) = 1 − 0.8327 = 0.1673.

2nd Method : P(X ≥ 8) = P(X = 8) + P(X = 9) + P(X = 10).

Houssein NASSER EL DINE 19 / 40

 Exercises

Exercise 3.
The population of a large city is 60% African-American. A jury of 12 is selected at random
from the citizens of the city. Let X be the number of African-American:
1 What model would you propose for X? Compute E(X) and V (X).
2 What is the probability that at most 3 African-American are selected?
3 What is the probability that at least 2 African-American are selected?
Solution:
1 Here we have 12 citizens, each one is either African-American or not, and the probability
of being African-American is constant 0.6, so

X ∼ B(n = 12, p = 0.6).

E[X ] = np = 12 × 0.6 = 7.2 Var(x) = npq = 12 × 0.6 × 0.4 = 2.88

2 P(X ≤ 3) = F (3) = 0.0153.
3 P(X ≥ 2) = 1 − P(X < 2) = 1 − P(X ≤ 1) = 1 − F (1) = 1 − 0.0003 = 0.9997.

Houssein NASSER EL DINE 20 / 40

 Exercises

Exercise 4.
Patients arrive at an emergency room in a hospital at an average rate of 6 per hour.
1 Find the probability that during any 90 minutes period the number of patients arriving at
an emergency room is
(a) Exactly 7.
(b) At least 10.
2 Find the probability that a patient arrives at an emergency room during 11:30 AM and
11:45 AM.
Solution:
1 Let X be the number of Patients arrive during any 90 minutes period
(t = 90 min = 1.5 hr), then

λt = 6 × 1.5 = 9 ⇒ X ∼ P(9),

e −9 (9)7
(a) P(X = 7) = f (7) = 7! = 0.11712.
(b) P(X ≥ 10) = 1 − P(X < 10) = 1 − F (9) = 1 − 0.5874 = 0.4126.

Houssein NASSER EL DINE 21 / 40

 Exercises

Houssein NASSER EL DINE 22 / 40

 Exercises

Exercise 4.
Solution:
2 Let Y be the number of Patients arrive between 11:30 AM and 11:45 AM
(t = 15 min = 0.25 hr), then

λt = 6 × 0.25 = 1.5 ⇒ Y ∼ P(1.5),

−1.5 1
e (1.5)
⇒ P(X = 1) = f (1) = 1!
= 0.33470.

Houssein NASSER EL DINE 23 / 40

 Exercises

Exercise 5.
Let X be a random variable representing the number of policies, a life insurance salesman
sells per week. It is known that the salesman sells on the average 3 life insurance policies per
week.
1 What model would you propose for X? Compute E(X) and V (X).
2 Calculate the probability that in a given week:
(a) he will sell 2 or more policies but less than 5 policies.
(b) he will sell more than 2 policies.
3 Assuming that there are 5 working days per week, what is the probability that in a given
day he will sell one policy?
Solution:
1 Let X be the number of policies sold per week, this is a count during a period of time
(t = 1 week ), then
λt = 3 × 1 = 3 ⇒ X ∼ P(3),
E[X ] = Var (X ) = λt = 3.

Houssein NASSER EL DINE 24 / 40

 Exercises

Houssein NASSER EL DINE 25 / 40

 Exercises

Exercise 5.
Solution:
2 We have:
(a) P(2 ≤ X < 5) = F (4) − F (1) = 0.8153 − 0.1991 = 0.6162.
2nd Method : P(2 ≤ X < 5) = P(X = 2) + P(X = 3) + P(X = 4)

32 33
−3 34
=e + + ( ).
2! 3! 4!
(b) P(X > 2) = 1 − P(X ≤ 2) = 1 − F (2) = 1 − 0.4232 = 0.5768.
1
3 Let Y be the number of policies sold in one day (t = 1 day = 5
week ), then

1
λt = 3 × = 0.6 ⇒ Y ∼ P(0.6),
5

e −0.6 (0.6)1
⇒ P(X = 1) = f (1) = = 0.329290.
1!
2nd Method : P(X = 1) = F (1) − F (0).

Houssein NASSER EL DINE 26 / 40

 Exercises

Exercise 6.
The number of industrial injuries per one working week in a particular factory is known to
follow a Poisson distribution with mean 0.5.
1 Find the probability that in a particular week there will be less than 2 accidents.
2 Find the probability that in a particular week there will be exactly 2 accidents.
3 Find the probability that in a particular week there will be more than one accident.
4 Find the probability that in a particular two weeks there will be more than 3 accidents.
Solution: X ∼ P(0.5) ⇒ λt = 0.5
1 P(X < 2) = P(X ≤ 1) = F (1) = 0.9098.
e −0.5 (0.5)2
2 P(X = 2) = f (2) = 2!
= 0.0758.

Houssein NASSER EL DINE 27 / 40

 Exercises

Houssein NASSER EL DINE 28 / 40

 Exercises

Exercise 6.
Solution:
3 P(X > 1) = 1 − P(X ≤ 1) = 1 − F (1) = 1 − 0.9098 = 0.0902.
4 Let Y be the number of industrial injuries per two working weeks (t = 2 weeks), then

λt = 0.5 × 2 = 1 ⇒ Y ∼ P(1),

⇒ P(X > 3) = 1 − P(X ≤ 3) = 1 − F (3) = 1 − 0.981 = 0.019.

Houssein NASSER EL DINE 29 / 40

 Exercises

Exercise 7.
Service calls come to maintenance center according to a Poisson distribution, and on
average, 3 calls are received per minute. Find the probability that :
1 No more than 4 calls come in any minute.
2 Fewer than 2 calls come in any minute.
3 Exactly 10 calls come in 3 minute-period.
Solution: t = 1 min ⇒ X ∼ P(3)
1 P(X ≤ 4) = F (4) = 0.8153.
2 P(X < 2) = P(X ≤ 1) = F (1) = 0.1991.
3 Let Y be the number of calls come in 3 minute-period (t = 3 mins), then

λt = 3 × 3 = 9 ⇒ Y ∼ P(9),

e −9 (9)10
⇒ P(X = 10) = = 0.1251.
10!

Houssein NASSER EL DINE 30 / 40

 Correlation coefficient

1 Poisson Distribution

2 Poisson Probability Table

3 Mean and Variance of a Poisson R.V.

4 Exercises

5 Correlation coefficient

6 Chebyshev’s Theorem

7 Geometric Distribution

8 Mean and Variance of a Geometric R.V.

Houssein NASSER EL DINE 31 / 40

 Correlation coefficient

Definition
Let X and Y be two R.V. with standard deviations σX and σY respectively. The Correlation
coefficient of X and Y is defined by:
σXY
ρXY = .
σX σY

We prove that −1 ≤ ρXY ≤ 1

Houssein NASSER EL DINE 32 / 40

 Chebyshev’s Theorem

1 Poisson Distribution

2 Poisson Probability Table

3 Mean and Variance of a Poisson R.V.

4 Exercises

5 Correlation coefficient

6 Chebyshev’s Theorem

7 Geometric Distribution

8 Mean and Variance of a Geometric R.V.

Houssein NASSER EL DINE 33 / 40

 Chebyshev’s Theorem

Theorem (Chebyshev’s Theorem)

The probability that any random variable X will assume a value within k times the standard
1
deviation of the mean is at least 1 − 2 that is
k
1
P(µ − k σ < X < µ + k σ) ≥ 1 −
k2

Remark:
The probability where the distance between the value of X and its mean is less than k times
1
its standard deviation is at least 1 − 2 :
k

µ − k σ < X < µ + k σ
1
⇐⇒ −k σ < X − µ < k σ =⇒ P(|X − µ| < k σ) ≥ 1 − 2
⇐⇒ |X − µ| < k σ
 k

Example:
A R.V has a mean µ = E(X ) = 8, a variance σ 2 = 9 ( with unknown probability
distribution).
a) Find P(−4 < X < 20).
b) Find P(|X − 8| ≥ 6).
Houssein NASSER EL DINE 34 / 40
 Chebyshev’s Theorem

Solution:
a)

P(−4 < X < 20) = P(−4 − 8 < X − 8 < 20 − 8)

= P(−12 < X − 8 < 12)
1 15
= P(|X − µ| < 12 = 4 × 3 = 4σ) ≥ 1 − =
42 16
b) P(|X − 8| ≥ 6) = 1 − P(|X − 8| < 6) but

1 3
P(|X − 8| < 6) = P(|x − µ| < 2σ) ≤ 1 − =
22 4
hence
3 1
P(|X − 8| ≥ 6) ≤ 1 − =
4 4

Houssein NASSER EL DINE 35 / 40

 Geometric Distribution

1 Poisson Distribution

2 Poisson Probability Table

3 Mean and Variance of a Poisson R.V.

4 Exercises

5 Correlation coefficient

6 Chebyshev’s Theorem

7 Geometric Distribution

8 Mean and Variance of a Geometric R.V.

Houssein NASSER EL DINE 36 / 40

 Geometric Distribution

Definition
The probability distribution of the Geometric R.V. X with parameter p, represents the number
of independent trials to obtain the first success where p is the probability of success and
1 − p the probability of failure, it is given by:

f (x) = (1 − p)x−1 p, x = 1, 2, 3 · · · .

where x can be any positive integer.

Example
In a repeated experiment of independent trials we assume P(S) = 0.6 & P(F ) = 0.4. Find
the probability that the first Success occurs on the six trial.
Solution: P(FFFFFS) = P(x = 6) = f (6) = 0.45 × 0.6 = 0.0061.

Notation
A R.V. X which is a Poisson R.V. is denoted by:

X ∼ GEO(p)

Houssein NASSER EL DINE 37 / 40

 Geometric Distribution

Exercise 1:
You play a game of chance that you can either win or lose (there are no other possibilities)
until you lose. Your probability of losing is p = 0.57 . What is the probability that it takes five
games until you lose? Let X = the number of games you play until you lose (includes the
losing game).

Exercise 2:
You throw darts at a board until you hit the center area. Your probability of hitting the center
area is p = 0.17. You want to find the probability that it takes eight throws until you hit the
center. What values does X take on?

Houssein NASSER EL DINE 38 / 40

 Mean and Variance of a Geometric R.V.

1 Poisson Distribution

2 Poisson Probability Table

3 Mean and Variance of a Poisson R.V.

4 Exercises

5 Correlation coefficient

6 Chebyshev’s Theorem

7 Geometric Distribution

8 Mean and Variance of a Geometric R.V.

Houssein NASSER EL DINE 39 / 40

 Mean and Variance of a Geometric R.V.

Rule
The mean and the variance of the Geometric distribution X ∼ GEO(p) are:

1 1−p
µ= , and V (X ) =
p p2

Exercise 3:
A safety engineer feels that 35% of all industrial accidents in her plant are caused by failure
of employees to follow instructions. She decides to look at the accident reports (selected
randomly and replaced in the pile after reading) until she finds one that shows an accident
caused by failure of employees to follow instructions. On average, how many reports would
the safety engineer expect to look at until she finds a report showing an accident caused by
employee failure to follow instructions? What is the probability that the safety engineer will
have to examine at least three reports until she finds a report showing an accident caused by
employee failure to follow instructions?

Houssein NASSER EL DINE 40 / 40