Chapter 5

Probability Distributions

Dr. Marwa Mostafa

Some Discrete Probability Distributions

1] Bernoulli Experiments
A Bernoulli trial is an experiment with two outcomes:
S≡ (success) and F≡ (failure)
P(S) = p and P(F) = q (= 1  p)

Example: Tossing a coin , S and F are contextually defined.

For a fair coin,
p = q =0.5
Dr. Marwa Mostafa
 Bernoulli Random Variables
A Bernoulli random variable, X, is defined by:
X = 1, if the outcome is Success,
X = 0, if the outcome is Failure.

X 1 0

P(X) p q

Dr. Marwa Mostafa

 Choosing a probability model

• The shape of a Bernoulli distribution: Bernoulli (p)

The Bernoulli experiment is a probability experiment that satisfies these
requirements:
• We have n=1 (One trial)
• The possible outcomes are: success (1) and failure (0)
• The probability of Success is p, the probability of Fail is q=1-p
• The variable of interest is the number of successes. X= 0 or 1
• The range of X is 0,1.

Dr. Marwa Mostafa

 Expectation and Variance of
Bernoulli Random Variable
A direct computation yields

(i)E (X)    (0)  q  (1)  p  p,

(ii )E (X 2 )  (0) 2 .q  (1)2 .p  p
then,
2
Var (X)  E (X )   2
2
 p  p  p(1Dr.Marwa  pq.
p) Mostafa
 4.2] The Binomial distribution:
It is a discrete distribution describes many experiments that
require the probability of the number of successes or failures
in a sample of repeated trials.

Dr. Marwa Mostafa

The following characteristics identify the binomial
experiment:
1- The experiment consists of a fixed number of trials denoted
by n.
2- The outcome of each trial can be classified as being either a
"success “ or a "failure".
3- The trials are independent.
4- The probability of success, denoted by p, remains the same
from trial to trial. The probability of failure equals q = 1-p.
5- The random variable x being studied is the number of
successes obtained in the n trials.

Dr. Marwa Mostafa

The Binomial Probability Function:
If X is a random variable having a binomial distribution then
its probability function is given by

 n  r n r
b(r, n, p)  P[X  r]    p q , r  0,1,2,...,n
r
0  p  1 , q  1-p
Where
n
   Cnr
= The number of ways that r objects can be selected
r
from n objects , n and p are called the parameters of the
binomial distribution .
Note that :
If n = 1 the binomial distribution is called the Bernoulli
Dr. Marwa Mostafa
distribution .
Dr. Marwa Mostafa
 The shape of a binomial distribution: B(n,p)
The binomial experiment is a probability experiment that satisfies these
requirements:
• Each trial can have only two possible outcomes—success or failure.
• There must be a fixed number of trials. n
• The outcomes of each trial must be independent of each other.
• The probability of success must remain the same for each trial. p
• The probability of Fail must remain the same for each trial. q=1-p
• The variable of interest is the number of successes. X
• The range of X is 0,1,2,…..,n
Dr. Marwa Mostafa
 The mean and variance of the
binomial distribution:
If X is binomial with parameters n and p , then X has

(a) mean = E(X) =  = n p and

(b) variance = Var(X) = 2 = n p q

Dr. Marwa Mostafa

Example (1): A driving examiner finds that he passes 40% of
the candidates. For a particular day on which he examines 9
people, find the probability that

(a) he passes exactly 6 people

(b) he passes at least one person

(c) he passes more than 7 people

(d) find the mean and the standard deviation of the number of
people who passes on that day , and then find
E(2X-1) and Var(-2X+4)
Dr. Marwa Mostafa
Solution:
Let X be the number of people he passes on that day,
then X has the binomial random variable with parameters
n = 9, p = 0.4 and q = 0.6, then
9
P[X  r ]    (0.4)r (0.6)9r , r  0, 1,..., 9
r
9 6 3
(a) P[ he passes 6 people ]  P[ X  6 ]  
6  ( 0. 4 ) ( 0 .6 )  0.0743
 
(b) P[ he passes at least one person ]  P[X  1]
 1 - P[ he passes none ]
 1 - P[X  0]
9
 1 -   (0.4)0 (0.6)9
Dr. Marwa Mostafa
0
 0.9899
(c) P[ he passes more than 7 people ]  P[X  7]  P[X  8]  P[X  9]
9 9
  (0.4) (0.6)    (0.4)9 (0.6)0
8 1

8 9
 0.0038

(d) E(X) = μ = n p = 9(0.4) = 3.6

Var(X) = σ2 = n p q = (9)(0.4)(0.6) = 2.16 ,

 Var (X )  2.16  1.47

Then,
E(2X-1) = 2 E(X) -1 = 2(np) – 1 = 2 (3.6) – 1 = 6.2
Var(-2X+4)= (-2)2 Var(X) Dr.
= Marwa
4 npq = 4 (2.16) = 8.64.
Mostafa
Example(2) : The probability that the noise level of a wide-
band amplifier will exceed 2 dB is 0.05. Find the probability
that among 12 such amplifiers the noise level of
(a) One will exceed 2 dB ;

(b) At most two will exceed 2 dB,

(c) Two or more will exceed 2 dB ;

Var ( 1 X  2)
(d) Compute  and, and then find E(5X+1) and
3

Dr. Marwa Mostafa

Solution :
Let, X = number of amplifiers for which the noise level will
exceed 2 dB, then X is a binomial random variable with
parameters n = 12, p = 0.05 and 1-p = 0.95

12 
P(X  r )    (0.05) r (0.95)12r , r  0, 1, 2,...,12
r

12 
(a) P(X  1)    (0.05)1 (0.95)11  0.341
1

Dr. Marwa Mostafa

(b) P(X ≤ 2) = P(X = 0) + P(X = 1) + P(X = 2), where

12 
P(X  0)    (0.05) 0 (0.95)12  0.54 &
0

12 
 
P(X  1)    (0.05) (0.95)  0.341 &
1 11

1
12 
P(X  2)    (0.05) 2 (0.95)10  0.099
2
Then, P(X ≤ 2) = 0.54 + 0.341 + 0.099 = 0.98

Dr. Marwa Mostafa

(c) P(X ≥ 2 ) = 1- (P(X = 0 ) + P(X = 1)

= 1- (0.54 + 0.341) = 0.119

(d) E(X) = µ = n p = (12) (0.05) = 0.6 &

  npq  (12)(0.05)(0.95)  0.755

Then ,
E(5X+1) = 5 E(X) + 1 = 5 (0.1) + 1 = 4

Var ( 1 X  2)  1 Var ( X )  0.755  0.084

3 9 9

Dr. Marwa Mostafa

Example (3) : If 20 % of the bolts produced by a machine are
defective , 4 bolts are chosen at random from the production of
these machine , what is the probability that
(a) one bolt is defective
(b) all 4 bolts will be good ,
(c) at most 2 bolts will be defective
(d) find the mean and the standard deviation of the number of
defective items in the sample

Solution:
X is a binomial random variable with parameters
n = 4, p = 0.2, then
 4 r (0.8) 4 r
P[ X  r ]  
r ( 0.2 ) , r  0,1,2,3,4
  Dr. Marwa Mostafa
  4
(a) P[ X  1]    (0.2)1 (0.8)3  0.4096
1
(b) P [all 4 bolts will be good]
 4 0 4
 P[X  0]   (0.2) (0.8)  0.4096
 0
(c) P[X  2]  P[X  0]  P[X  1]  P[X  2]
 4  4
  (0.2) (0.8)   (0.2)1 (0.8)3 
0 4

0 1
 4 2 2
 (0.2) (0.8)
 2
 0.9728
Dr. Marwa Mostafa
(d) E(X) = μ = n p = 4(0.2) = 0.8

Var(X) = σ2 = n p q = (4)(0.2)(0.8) = 0.64

  0.64  0.8

Dr. Marwa Mostafa

Example(4): It is known that disks produced by a certain
company will be defective with probability 0.01 independently
of each other . The company sells the disks in packages of 10
and offers a money-back guarantee that at most 1 of the 10
disks is defective.
(a) What proportion of packages is returned ?
(b) If someone buys three packages , what is the probability
that exactly one of them will be returned ?

Dr. Marwa Mostafa

Solution: Let X represents the number of defective
disks in a package , then assuming that customers always take
advantage of the guarantee, it follows that X is binomial
random variable with parameters
n = 10, p =0.01. Hence
(a) The probability that a package will have to be replaced is

P[X  1]  1  P[X  0]  P[X  1]

10  10 
 1 -   (0.01) (0.99)    (0.01)1 (0.99)9
0 10
0 1
 0.005

Dr. Marwa Mostafa

(b) Because each package will independently , have to be
replaced with probability 0.05 . It is follows that the number of
packages that the person will have to run is a binomial random
variable with parameters n = 3 , and p = 0.005 .
Therefore , the probability that exactly one of the three
packages will returned is

 3 1 2
P[ X  1]    (0.005) (0.995)  0.015
1

Dr. Marwa Mostafa

Example(5) : A communications system consists of n
components , each of which will, independently, function with
probability p . The total system will be able to operate
effectively if at least one-half of its components function .
For what value of p is a 5-component system more likely to
operate effectively than a 3-component system ?

Dr. Marwa Mostafa

Solution :
Because the number of functioning components is a binomial
random variable with parameters (n, p) , it follows that the
probability that a 5-component system will be effective is

P[ at least one - half of its componentsfunction ]

 P[X  3]
 P[X  3]  P[X  4]  P[X  5]
 5 3  5 4  5 5
  p (1  p)    p (1  p)    p (1  p)0
2 1
 3  4  5
 10p3 (1  p) 2  5p 4 (1  p)  p5

whereas the corresponding probability for a 3-component

system is Dr. Marwa Mostafa
 P[ at least one - half of its componentsfunction ]
 P[ X  2]
 P[ X  2]  P[ X  3]
 3 2 1   3 3 0
 
 2 p (1 - p)  
 3 p (1  p )
   
 3p 2 (1  p)  p3

Hence, the 5-component system is better if

10p3 (1  p)2  5p 4 (1  p)  p5  3p 2 (1  p)  p3
which , reduces to
3(p - 1)2 ( 2p  1)  0

or, p ≥ ½ Dr. Marwa Mostafa

Example (6): A multiple-choice test consists of 12 questions
each with 5 possible answers of which only 1 is the correct
answer. An ill-prepared candidate guesses the answer to each
question. Given that each correct answer scores 4 marks and
each wrong answer scores minus one mark, find the
probabilities that the candidate scores
(a) 13 marks
(b) less than zero marks

Solution: Let X represents the number of correct answers due

to guesswork, then X has the binomial random variable with
parameters
n = 12, p =1/5 and , q = 4/5 then
Dr. Marwa Mostafa
 12  r 12 r
P[X  r ]   (0.2) (0.8) , r  0,1,...,12
r

12  5 7
(a) P[ 13 marks]  P[X  5]   (0.2) (0.8)  0.0532
5

(b) P[ Less than 0 marks ]  P[X  0, 1 or 2]

 P[X  0]  P[X  1]  P[X  2]
 0.0687  0.2062 0.2835
 0.5583
Dr. Marwa Mostafa
Example (7):
It has been claimed that 60% of all solar-heat installations the
utility bill is reduced by at least one-third. Accordingly, what
are the probabilities that the utility bill will be reduced by at
least one-third in
(a) Four of five installations;
(b) At least four of five installation;
(c) Find the mean and the standard deviation

Solution: Let X represents the number of solar-heat

installations that the utility bill is reduced by at least one-third.
Then X has the binomial random variable with parameters
n = 5, p =0.6 and , q = 0.4 then
Dr. Marwa Mostafa
 5 5 r
P[X  r]    (0.6) (0.4)
r
, r  0,1, 2,3, 4,5.
r
5
(a) P[X  4]    (0.6) 4 (0.4)1  0.259
 4

(b) P[X  4]= P[X  4]  P[X  5]

5  5
   (0.6) (0.4) +   (0.6) (0.4)
4 1 5 0

 4  5
 0.259 +0.078=0.337
Dr. Marwa Mostafa
(c) E(X) = μ = n p = 5(0.6) = 0.3

Var(X) = σ2 = n p q = (5)(0.6)(0.4) = 1.2

  1.2  1.1

Dr. Marwa Mostafa

Example (8):
If the probability is 0.05 that a certain wide-flange column will
fail under a given axial load, what are the probabilities that
among 16 such columns
(a) At most two will fail;
(b) At least four will fail;
(c) Find the mean and the standard deviation
Solution: Let X represents the number of wide-flange column
that fail under a given axial load. Then X has the binomial
random variable with parameters
n = 16, p =0.05 and , q = 0.95 then

Dr. Marwa Mostafa

 16  16  r
P[X  r]    (0.05) (0.95)
r
, r  0,1, 2,...,16.
r

(a) P[X  2]= P[X=0]+P[X  1]  P[X  2]

16  16 
   (0.05) (0.95) +   (0.05)1(0.95)15 
0 16

0 1
16 
  (0.05) 2
(0.95)14
 0.4401 +0.3706+0.1463=0.957
2

Dr. Marwa Mostafa

(b) P[X  4] =1-( P[X=0]+P[X  1]  P[X  2]  P[X  3])

 16  16  
   (0.05) (0.95) +   (0.05) (0.95)  
0 16 1 15

 0 1 
 1
 16   16  
   (0.05) 2 (0.95)14 +   (0.05)3 (0.95)13 
 2 3 
     

 1-(0.4401 +0.3706+0.1463+0.0360)=0.0071

(c) E(X) = μ = n p = 16(0.05) = 0.8

Var(X) = σ2 = n p q = (16)(0.05)(0.95) = 0.76
  0.76  0.872
Dr. Marwa Mostafa
B] Continuous Distributions
•Normal (Gauss) Distribution
A random variable X is said to have normal distribution iff its p.d.f is
given as


2
1  x  
1   
 e 2  
x 
f ( x )   2 2

 0 otherwise

where

Dr. Marwa Mostafa

Dr. Marwa Mostafa
Its properties:
•Its symmetric around the mean x=

,i.e. the area under the curve =1

•The st. line x=
divides the curve into two equal halves i.e. the area on each side = 0.5
•The function is increasing on the ] - [.

and decreasing on the interval [ ]

Dr. Marwa Mostafa

•Standard Normal Distribution
A random variable X has a standard normal distribution iff its p.d.f is

 1 1
 z2
 e 2
z 
f (z )   2 2
0 otherwise

with

thus it is denoted by N(0,1).

To get the standard form let

Dr. Marwa Mostafa

It is symmetric around the st. line x=0.

Dr. Marwa Mostafa

Dr. Marwa Mostafa
 P( -a ≤ Z ≤ a)=
P(Z ≤ 0 ) = P( Z ≥ 0 ) = P( Z ≤ a) =
P( Z ≤ - a) =
P(Z ≥ a)

P( a ≤ Z ≤ b) = P( -a ≤ Z ≤ b) =
P( Z ≤ b) = P( -a ≤ Z ≤ -b) =
P( -b ≤ Z ≤ a ) =

Dr. Marwa Mostafa

Example 1: Find the area to the left of z = 1.99.
 (1.99)  P ( Z  1.99)

The value in the 1.9 row and the .09 column of

the table is 0.9767. The area is 0.9767.
Dr. Marwa Mostafa
Example 2: Find the area to right of z = -1.16.
P ( Z  1.16)  P( Z  1.16)

The value in the 1.1 row and the .06 column of

the table is 0.8770. The area is 0.8770.
Dr. Marwa Mostafa
Examples 3 and 4:

P ( Z  1.5)  1  P ( Z  1.5) P ( Z  1.83)  P ( Z  0)

(a) The value for z = 1.5 is 0.9332.The area is 0.0668

(b) The values for z = 1.83 and z =0 is 0.9664 and 0.5
The area is 0.9664-0.5Dr.=Marwa
0.4664
Mostafa
Example 5: Find the area between z = 1.68 and
z = -1.37.
P (1.37  Z  1.68)  P( Z  1.68)  P( Z  1.37)
 P ( Z  1.68)  1  P( Z  1.37) 

The values for z = 1.68 is 0.9535 and for z = 1.37

is 0.9147. The areaDr.is 0.8682.
Marwa Mostafa
Example 2: Find the z value such that the area
under the standard normal distribution curve
between 0 and the z value is 0.21.

P ( Z  z )  0.5  0.21 Dr.0.71 then z  q  q0.71  0.5534

Marwa Mostafa
 0.88
Example 3:

0.06

P(-k ≤ Z ≤ k ) = 0.88
0.94

\ P(-k ≤ Z ≤ k ) = 0.88
the area below –k is equal to 0.06

Dr. Marwa Mostafa

Example :
The RV Z is standard normal.
Find the probability that
(a) Z ≤ 2.44
(b) Z ≤ – 1.16
(c) Z ≥ 1
(d) 1 ≤ Z ≤ 1.8
Exercise:
(e) |z| ≤ k = 2.14
(f) k ≤ Z ≤ 2.1 = 0.1
(g) 1.3 ≤ Z ≤ k = 0.3710

Sol:
(a) P(Z ≤ 2.44) = F(2.44) = Φ(2.44) =….
(b) P(Z ≤ – 1.16) = F (– 1.16) = Φ(– 1.16) = 1 – Φ(1.16) =….
(c) P(Z ≥ 1) = 1 – F (1) = 1 – Φ(1) =….
(d) P(1 ≤ Z ≤ 1.8) = F(1.8) – F (1) = Φ(1.8) – Φ(1) = ….
Dr. Marwa Mostafa
Section 4: Calculations using tables
Section 4.3: The standard normal distribution
(z value or standard score)

– If , then the random variable

– Conversely, if ,then the random variable

– X    z (Important)
Dr. Marwa Mostafa
 Example 1:
A survey by the National Retail Federation found that
women spend on average $146.21 for the Christmas
holidays. Assume the standard deviation is $29.44. Find
the percentage of women who spend less than $160.00.
Assume the variable is normally distributed.

Step 1: Draw the normal distribution curve.

Dr. Marwa Mostafa

 Example 1:
Step 2: Find the z value corresponding to $160.00.
X  160.00  146.21
z   0.47
 29.44
Step 3: Find the area to the left of z = 0.47.

P ( X  160)  P ( Z  0.47)  0.6808.

Table 1 gives us an area of 0.6808.

68% of women spend lessMostafa
Dr. Marwa than $160.
 Example 2: Engineer Academy
To qualify for an engineer academy, candidates must
score in the top 10% on a general abilities test. The test
has a mean of 200 and a standard deviation of 20. Find
the lowest possible score to qualify. Assume the test
scores are normally distributed.

Step 1: Draw the normal distribution curve.

Dr. Marwa Mostafa

 Example 2: Police Academy
Step 2:

P ( Z  z )  0.1 then z  q1

z  q1  q0.9  1.282

Step 3: Find X.

X    z  200  1.28  20   225.60

The cutoff, the lowest possible score to qualify, is 226.

Dr. Marwa Mostafa