CHAPTER FOUR

PROBABILITY THEORY AND PROBABILITY DISTRIBUTION

4.1 PROBABILITY THEORY

We use the concept of probability to deal with uncertainty. Intuitively, the probability of an event is a
number that measures the chance, or likelihood, that the event will occur. For instance, the probability that
your favorite football team will win its next game measures the likelihood of a victory. The probability of
an event is always a number between 0 and 1. The closer an event’s probability is to 1, the higher is the
likelihood that the event will occur; the closer the event’s probability is to 0, the smaller is the likelihood
that the event will occur. For example, if you believe that the probability that your favorite football team
will win its next game is 0.95, then you are almost sure that your team will win. However, if you believe
that the probability of victory is only 0.10, then you have very little confidence that your team will win.
SOME BASIC CONCEPTS
Probability, in common parlance, refers to the chance of occurrence of an event or happening. In order that
we are able to compute it, a proper understanding of certain basic concepts in probability theory is required.
These concepts are an Experiment, a Sample space, and an Event.
EXPERIMENT
A random experiment is a mechanism that produces a definite outcome that cannot be predicted with
certainty. An outcome of an experiment is some observation or measurement. Any action, whether it is the
drawing a card out of a deck of 52 cards, or reading the temperature, or measurement of a product's
dimension to ascertain quality, or the launching of a new product in the market, constitute an experiment in
the probability theory terminology.
The experiments in probability theory have three things in common:
 there are one or more outcomes of each experiment
 it is possible to specify the outcomes in advance
 there is uncertainty about the outcomes
A single outcome of an experiment is called a basic outcome or an elementary event. Any particular card
drawn from a deck is a basic outcome.
SAMPLE SPACE
The Sample space is the universal set S pertinent to a given experiment. It is the set of all possible
outcomes of an experiment. So each outcome is visualized as a sample point in the sample space. The
sample spaces for the following experiments are:
Experiment Sample Space
Drawing a Card {all 52 cards in the deck}
Reading the Temperature {all numbers in the range of temperatures}
Measurement of a Product's {undersize, outsize, right size}
Dimension
Launching of a New Product {success, failure}

EVENT
An event, in probability theory, constitutes one or more possible outcomes of an experiment. An Event is a
subset of a sample space. It is a set of basic outcomes. We say that the event occurs if the experiment gives
rise to a basic outcome belonging to the event. For the experiment of drawing a card, we may obtain
different events.

APPROACHES TO PROBABILITY THEORY

1|Page
We often wish to assign probabilities to sample space outcomes. This is usually done by using one of three
methods: the classical method, the relative frequency method, or the subjective method. Regardless of the
method used, probabilities must be assigned to the experimental outcomes so that two conditions are met:
1. The probability assigned to each sample space outcome must be between 0 and 1. That is, if E
represents a sample space outcome and if P(E) represents the probability of this outcome, then 0 ≤
P(E) ≤ 1.
2. The probabilities of all of the sample space outcomes must sum to 1.

THE CLASSICAL APPROACH

The classical method of assigning probabilities can be used when the sample space outcomes are equally
likely. For example, consider the experiment of tossing a fair coin. Here, there are two equally likely
sample space outcomes—head (H) and tail (T). Therefore, logic suggests that the probability of observing a
head, denoted P(H), is 1/2 = 0.5, and that the probability of observing a tail, denoted P(T), is also 1/2 = 0.5.
Notice that each probability is between 0 and 1. Furthermore, because H and T are all of the sample space
outcomes, P(H) + P(T) = 1. In general, if there are N equally likely sample space outcomes, the probability
1
assigned to each sample space outcome is . To illustrate this, consider the experiment of rolling a fair die.
N
It would seem reasonable to think that the six sample space outcomes 1, 2, 3, 4, 5, and 6 are equally likely,
and thus each outcome is assigned a probability of 1/6. If P(1) denotes the probability that one dot appears
on the upward face of the die, then P(1) = 1/6. Similarly, P(2) = 1/6, P(3) = 1/6, P(4) = 1/6, P(5) = 1/6, and
P(6) = 1/6.
In the Classical Approach, probability of an event is defined as the relative size of the event with respect to
the size of the sample space. The rule we use in computing probabilities, assuming equal likelihood of all
basic outcomes, is as follows:
Probability of the event A:
n( A)
P ( A )=
N ( S)

Where, n (A) = the number of outcomes favorable to the event A

N (S) = total number of outcomes
Example: 1
A fair coin is tossed twice. Find the probabilities of the following events:
a) A, getting two heads
b) B, getting one head and one tail
c) C, getting at least one head or one tail
d) D, getting four heads
Answer:To find the probabilities of the events A, B, C, and D when a fair coin is tossed twice, we can use
the concept of probability.
Event A: Getting two heads
When a fair coin is tossed twice, the sample space consists of 4 possible outcomes: HH, HT, TH, TT (H
represents head and T represents tail).
The event of getting two heads is HH.
Number of favorable outcomes = 1
Total number of outcomes = 4
Probability of getting two heads (A) = Number of favorable outcomes / Total number of outcomes = 1 / 4 =
0.25

Event B: Getting one head and one tail

2|Page
The event of getting one head and one tail can happen in two ways: HT or TH.
Number of favorable outcomes = 2
Total number of outcomes = 4
Probability of getting one head and one tail (B) = Number of favorable outcomes / Total number of
outcomes = 2 / 4 = 0.5

Event C: Getting at least one head or one tail

This event includes all outcomes except for TT (no heads or tails).
Number of favorable outcomes = 3 (HH, HT, TH)
Total number of outcomes = 4
Probability of getting at least one head or one tail (C) = Number of favorable outcomes / Total number of
outcomes = 3 / 4 = 0.75

Event D: Getting four heads

There is only one way to get four heads, which is HH.
Number of favorable outcomes = 0 (as there are no such outcomes)
Total number of outcomes = 4
Probability of getting four heads (D) = Number of favorable outcomes / Total number of outcomes = 0 / 4 =
0

Therefore, the probabilities for the events A, B, C, and D are as follows:

A. Probability of getting two heads = 0.25
B. Probability of getting one head and one tail = 0.5
C. Probability of getting at least one head or one tail = 0.75
D. Probability of getting four heads = 0
THE RELATIVE FREQUENCY APPROACH
The Relative Frequency Approach is used to compute probability in which there is only a past data. In the
absence of past data, we have to undertake an experiment. As per this approach, the probability of
occurrence of an event is given by the observed relative frequency of an event in a very large number of
trials. In other words, the probability of occurrence of an event is the ratio of the number of times the event
occurs to the total number of trials. For example, to estimate the probability that a randomly selected
consumer prefers Coca-Cola to all other soft drinks, we perform an experiment in which we ask a randomly
selected consumer for his or her preference. There are two possible experimental outcomes: “prefers Coca-
Cola” and “does not prefer Coca-Cola.” However, we have no reason to believe that these experimental
outcomes are equally likely, so we cannot use the classical method. We might perform the experiment, say,
1,000 times by surveying 1,000 randomly selected consumers. Then, if 140 of those surveyed said that they
prefer Coca-Cola, we would estimate the probability that a randomly selected consumer prefers Coca-Cola
to all other soft drinks to be 140/1,000 = 0.14. This is an example of the relative frequency method of
assigning probability. The probability of the event B:

n
P ( B )=
N
Where, n = the number of times the event occurs
N = total number of trials
Example: 2
A newspaper boy wants to find out the chances that on any day he will be able to sell more than 90 copies
of The Times of Ethiopia. From his dairy where he recorded the daily sales of the last year, he finds out that
out of 365 days, on 75 days he had sold 80 copies, on 144 days he had sold 85 copies, on 62 days he had

3|Page
sold 95 copies and on 84 days he had sold 100 copies of The Times of Ethiopia. Find out the required
probability for the newspaper boy.

Answer:To find the probability that the newspaper boy will be able to sell more than 90 copies of The
Times of Ethiopia on any given day, we need to calculate the total number of days he sold more than 90
copies and divide it by the total number of days in a year.
From the given data:
- Number of days he sold 80 copies = 75
- Number of days he sold 85 copies = 144
- Number of days he sold 95 copies = 62
- Number of days he sold 100 copies = 84
To find the total number of days he sold more than 90 copies:
Total number of days he sold more than 90 copies = Number of days he sold 95 copies + Number of days
he sold 100 copies
Total number of days he sold more than 90 copies = 62 + 84 = 146

Total number of days in a year = 365

Probability of selling more than 90 copies on any given day = Number of days he sold more than 90
copies / Total number of days in a year
Probability = 146 / 365
Probability ≈ 0.4

Therefore, the required probability for the newspaper boy to sell more than 90 copies of The Times of
Ethiopia on any given day is approximately 0.4.

THE SUBJECTIVE APPROACH

In this approach, we try to assess the probability from our own experiences. We may bring in any
information to assess this. Therefore the Subjective Approach involves personal judgment, information,
intuition, and other subjective evaluation criteria. The area of subjective probability - which is relatively
new, having been first developed in the 1930s – is somewhat controversial. One person's subjective
probability may very well be different from another person's subjective probability of the same event. We
may note here that since the assessment is a purely subjective one, it will vary from person to person and,
therefore, subjective probability is also called Personal Probability.
Example: 3
In a certain situation, one might express the confidence that there are 70:30 chances of a salesman
achieving his sales quote.

Answer: When someone expresses that there are 70:30 chances of a salesman achieving his sales quote,
they are essentially stating the probability or likelihood of the event happening. In this case, the ratio 70:30
can be interpreted as a probability.

To convert the 70:30 ratio into a probability, you can divide the first number by the sum of both numbers:

Probability = 70 / (70 + 30) = 70 / 100 = 0.7

Therefore, when someone says there are 70:30 chances of a salesman achieving his sales quote, it means
there is a 70% probability of the salesman meeting his sales target.

4|Page
Some Elementary Probability Rules
We can often calculate probabilities by using formulas called probability rules. We will begin by
presenting the simplest probability rule: the rule of complements. To start, we define the complement of an
event:
The Rule of Complements defines the probability of the complement of an event in terms of the probability
of the original event. Consider event A defined over the sample space S. The complement of an event A in
a sample space S, denoted by Ac , is the collection of all outcomes in S that are not elements of the set A.
(see Figure 1)
P( A¿ ¿ c)=1−P( A)¿

Figure 1 Complement of an event

As a simple example, if the probability of rain tomorrow is 0.3, then the probability of no rain tomorrow
must be 1 - 0.3 = 0.7. If the probability of drawing a king is 4/52, then the probability of the drawn card's
not being a king is 1 - 4/52 = 48/52.

THE UNION RULE

A very important rule in probability theory, the Rule of Unions (also called Addition Theorem) allows us
to write the probability of the union of two events in terms of the probabilities of the two events and the
probability of their intersection.
Consider two events A and B defined over the sample space S, as shown in the following Figure

Figure 2 Two Overlapping Events A and B

Thus, the rule of unions is:

P ( A ∪ B )=P ( A ) + P ( B ) −P( A ∩ B)

The probability of the intersection of two events P ( A ∩B ) is called their joint probability.

Example: 4
A card is drawn from a well-shuffled pack of playing cards. Find the probability that the card drawn is
either a club or a king.

Answer : There are 52 cards in a standard deck of playing cards.

5|Page
There are 13 clubs in a deck, and there are 4 kings (one king in each suit). However, one of the kings is also
a club (the king of clubs), so we don't want to count it twice.

Therefore, there are 13 - 1 = 12 clubs that are not kings, plus the 3 remaining kings, for a total of 12 + 3 =
15 cards that are either a club or a king.

So, the probability of drawing a card that is either a club or a king is:

P(club or king) = Number of favorable outcomes / Total number of outcomes

P(club or king) = 15 / 52
P(club or king) = 0.2885

Therefore, the probability that the card drawn is either a club or a king is approximately 0.2885 or 28.85%.

Mutually Exclusive Events

Two events A and B are mutually exclusive if they have no sample space outcomes in common. In this
case, the events A and B cannot occur simultaneously, and thus P(A ∩ B) = 0

Figure 3 Two Mutually Exclusive Events A and B

This fact gives us a special rule for unions of mutually exclusive events. Since the probability of the
intersection of the two events is zero, there is no need to subtract P (A∩B) when the probability of the
union of the two events is computed.
Therefore, For mutually exclusive events A and B:
P (A ∪ B) = P (A) + P (B)
This is not really a new rule since we can always use the rule of unions for the union of two events: If the
events happen to be mutually exclusive, we subtract zero as the probability of the intersection.
Example: 5
A card is drawn from a well-shuffled pack of playing cards. Find the probability that the card drawn is
either a king or a queen.
We can extend the Rule of Unions to three (or more) events. Let A, B, and C be the three events defined
over the sample space S, as shown in Figure 4
Then, the Rule of Unions is
P (A∪B∪C) = P (A) + P (B) + P (C) − P (A∩B) − P (B∩C) − P (A∩C) + P (A∩B ∩C)

6|Page
Figure 4 Three Overlapping Events A, B and C

When the three events are mutually exclusive (see Figure 5), the Rule of Unions is
P (A∪B∪C) = P (A) + P (B) + P (C)

Figure 5 Three Mutually Exclusive Events A, B and C

Example: 6
A card is drawn from a well-shuffled pack of playing cards. Find the probability that the card drawn is
a) either a heart or an honour or king
b) either an ace or a king or a queen.

To find the probability that the card drawn is either a heart or an honor or a king, we need to determine the
number of cards that fall into each category and then calculate the total number of favorable outcomes.

1. Hearts: There are 13 hearts in a deck.

2. Honors (Jacks, Queens, Kings): There are 3 suits (Hearts, Diamonds, Spades) with 3 honor cards each,
so there are a total of 3 * 3 = 9 honor cards.

3. Kings: There are 4 kings in a deck.

To avoid double counting the king of hearts (which is both a heart and a king), we will subtract it from the
total count of kings, so there are 4 - 1 = 3 kings that are not hearts.

Now, let's calculate the total number of favorable outcomes:

Total favorable outcomes = Number of hearts + Number of honors + Number of kings

Total favorable outcomes = 13 + 9 + 3
Total favorable outcomes = 25

The total number of cards in a deck is 52. Therefore, the probability that the card drawn is either a heart or
an honor or a king is:

7|Page
P(heart or honor or king) = Number of favorable outcomes / Total number of outcomes
P(heart or honor or king) = 25 / 52
P(heart or honor or king) ≈ 0.4808

Therefore, the probability that the card drawn is either a heart or an honor or a king is approximately 0.4808
or 48.08%.

Now, let's find the probability that the card drawn is either an ace or a king or a queen:

1. Aces: There are 4 aces in a deck.

2. Kings: We already determined there are 4 kings (excluding the king of hearts).
3. Queens: There are 4 queens in a deck.

Now, let's calculate the total number of favorable outcomes:

Total favorable outcomes = Number of aces + Number of kings + Number of queens

Total favorable outcomes = 4 + 4 + 4
Total favorable outcomes = 12

The total number of cards in a deck is still 52. Therefore, the probability that the card drawn is either an ace
or a king or a queen is:

P(ace or king or queen) = Number of favorable outcomes / Total number of outcomes

P(ace or king or queen) = 12 / 52
P(ace or king or queen) ≈ 0.2308

Therefore, the probability that the card drawn is either an ace or a king or a queen is approximately 0.2308
or 23.08%.
THE CONDITIONAL PROBABILITY RULE
As a measure of uncertainty, probability depends on information. We often face situations
where the probability of an event A is influenced by the information that another event B
has occurred. Thus, the probability we would give the event "XYZ Company’s stock price
will go up tomorrow" depends on what we know about the company and its performance;
the probability is conditional upon our information set. In this example, event A may be the
event that the stock will go up tomorrow, and event B may be a favorable quarterly report.
Consider two events A and B defined over the sample space S, as shown below in Figure 6

Figure 6 Conditional Probability of Event A

8|Page
Conditional Probability
1. The conditional probability of the event A given that the event B has occurred is written P(A |B) and
is defined to be
P( A ∩ B)
P( A /B)=
P(B)
Here we assume that P(B) is greater than 0.
2. The conditional probability of the event B given that the event A has occurred is written P(B | A) and
is defined to be
P( A ∩ B)
P(B/ A)=
P (A )
Here we assume that P(A) is greater than 0.

The vertical line in P (A / B) is read given, or conditional upon.

Example: 7
For an experiment of throwing a die twice, find the probability:
a) of the event of getting a total of 9, given that the die has shown up points between 4 and 6 (both
inclusive)
b) of the event of getting points between 4 and 6 (both inclusive), given that a total of 9 has already
been obtained

Solution :n ( A )=4 ; n ( B )=9; n ( A ∩ B )=2

2
P ( A ∩ B ) 36 2
P ( A / B )= = = =0.22
P ( B) 9 9
36

2
P ( A ∩ B ) 36 2
P ( B / A )= = = =0.5
P( A) 4 4
36
THE PRODUCT RULE
The Product Rule (also called Multiplication Theorem) allows us to write the probability of the
simultaneous occurrence of two (or more) events.
In the conditional probability rules

P( A ∩ B) P(B∩ A)
P( A /B)= ¿ P ( B / A )=
P(B) P (A )

A ∩ B or B ∩ A is the event A and B occur simultaneously. So rearranging the conditional probability rules,
we have our Product Rule
P ( A ∩B )=P ( A /B ) × P ( B ) ∧P ( A ∩ B )=P ( B/ A ) × P ( A )

Example: 8
A box contains 10 balls out of which 2 are green, 5 are red and 3 are black. If two balls are drawn at
random, one after the other without replacement, from the box. Find the probabilities that:
9|Page
(a) both the balls are of green color
(b) both the balls are of black color
(c) both the balls are of red color
(d) the first ball is red and the second one is black
(e) the first ball is green and the second one is red
Solution:
a ¿ P ( G1 ∩ G2) =P ( G2 /G1) × P ( G1 )

P ( G1 ∩G 2 ) =()( )
1
9
×
2 2 1
= = =0.022
10 90 45

b ¿ P ( B1 ∩ B2 ) =P ( B2 / B1 ) × P ( B 1)

P ( B 1 ∩ B2 )=()( )
2
9
×
3 6
= = =0.067
10 90 15
1

c ¿ P ( R 1 ∩ R2 ) =P ( R 2 /R 1 ) × P ( R 1 )

P ( R1 ∩ R 2 )= ()( )
4
9
×
5 20 2
= = =0.22
10 90 9

d ¿ P ( R 1 ∩ B2 )=P ( B2 / R1 ) × P ( R1 )

P ( R1 ∩ B2 ) =()( )
3
9
×
5 15 1
= = =0.17
10 90 6

e ¿ P ( G1 ∩ R2 )=P ( R2 /G1 ) × P ( G1 )

P ( G 1 ∩ R 2) =()( )
5
9
×
2 10 1
= = =0.11
10 90 9
Independent Events
Two events are said to be independent of each other if the occurrence or non-occurrence of one event in
any trial does not affect the occurrence of the other event in any trial. Events A and B are independent of
each other if and only if the following three conditions hold:
When A and B are independent (and only when they are independent), we can obtain the probability of the
joint occurrence of A and B (i.e. the probability of their intersection) simply by multiplying the two
separate probabilities. This rule is thus called the Product Rule for Independent Events.

Conditions for the independence of two events A and B:

P ( A / B ) = P ( A)
P (B / A) = P (B )
and P ( A ∩ B ) = P ( A). P (B )
Here we assume that P(A) and P(B) are greater than 0.
The first two equations have a clear, intuitive appeal. The top equation says that when A and B are
independent of each other, then the probability of A stays the same even when we know that B has occurred
- it is a simple way of saying that knowledge of B tells us nothing about A when the two events are
independent. Similarly, when A and B are independent, then knowledge that A has occurred gives us
absolutely no information about B and its likelihood of occurring.
The third equation, however, is the most useful in applications. It tells us that when A and B are
independent (and only when they are independent), we can obtain the probability of the joint occurrence of

10 | P a g e
A and B (i.e. the probability of their intersection) simply by multiplying the two separate probabilities. This
rule is thus called the Product Rule for Independent Events.
A Counting Rule for Multiple-Step Experiments
If an experiment can be described as a sequence of k steps in which there are n1 possible outcomes on the
first step, n2 possible outcomes on the second step, and so on, then the total number of experimental
outcomes is given by (n1)(n2) . . . (nk).
Example 9: Now suppose the student takes a class quiz consisting of three true–false questions. Then, there
are (n1)(n2)(n3) = (2)(2)(2) = 8 experimental outcomes. If the student is totally unprepared for the quiz and
has to blindly guess the to each question, the 8 experimental outcomes might be considered to be equally
likely. Therefore, since only one of these outcomes corresponds to all three questions being Answered
correctly, the probability that the student will answer all three questions correctly is 1/8.
A Counting Rule for Combinations
The number of combinations of n items that can be selected from N items is
n!
nC r=
r !(n−r )!
where, n! = n(n-1) (n-2).....1
r! = r(r-1) (r-2)........1
Example : 10
Among 15 clocks there are two defectives. In how many ways can an inspector chose three of the clocks for
inspection so that:
a) There is no restriction.
b) None of the defective clock is included.
c) Only one of the defective clocks is included.
d) Two of the defective clock is included.
Solutions:
n 15 of which 2 are defective and 13 are non  defective .
r 3
a) If there is no restriction select three clocks from 15 clocks and this can be done in :
n! 15 !
nC r= =15 C3 = =455 ways
r !(n−r )! 3 ! (12)!
b) None of the defective clocks is included.
This is equivalent to zero defective and three non defective, which can be done in:
2! 13 !
2 C0 ×13 C 3= × =286 ways
0 !(2)! 3 !(10)!
c) Only one of the defective clocks is included.
This is equivalent to one defective and two non defective, which can be done in:\
2! 13!
2 C1 ×13 C 2= × =156 ways
1 !(1)! 2 !(11)!
d) Two of the defective clock is included.
This is equivalent to two defective and one non defective, which can be done in:
2! 13 !
2 C2 ×13 C 1= × =13 ways
2 !(0)! 1! (12)!
Exercises:
1. Out of 5 Mathematician and 7 Statistician a committee consisting of 2 Mathematician and 3
Statistician is to be formed. In how many ways this can be done if
a) There is no restriction
b) One particular Statistician should be included
11 | P a g e
 c) Two particular Mathematicians cannot be included on the committee.
Answer
A. To form a committee of 2 Mathematicians and 3 Statisticians without any restriction, we can use the
combination formula:
Total ways = C(5, 2) * C(7, 3)
Total ways = 10 * 35
Total ways = 350
Therefore, the committee can be formed in 350 ways without any restriction.
B. If one particular Statistician should be included in the committee, we have to choose 2 Mathematicians
from the remaining 4 Mathematicians and 2 Statisticians from the remaining 6 Statisticians:
Total ways = C(4, 2) * C(6, 2)
Total ways = 6 * 15
Total ways = 90
Therefore, the committee can be formed in 90 ways with one particular Statistician included.
C. If two particular Mathematicians cannot be included in the committee, we have to choose 2
Mathematicians from the remaining 3 Mathematicians and 3 Statisticians from the 7 Statisticians:
Total ways = C(3, 2) * C(7, 3)
Total ways = 3 * 35
Total ways = 105
Therefore, the committee can be formed in 105 ways with two particular Mathematicians excluded.
2. If 3 books are picked at random from a shelf containing 5 novels, 3 books of poems, and a
dictionary, in how many ways this can be done if
a) There is no restriction.
b) The dictionary is selected?
c) 2 novels and 1 book of poems are selected?
Answer
A. To pick 3 books at random without any restriction, we can use the concept of combinations:
Total ways = C(9, 3)
Total ways = 84
Therefore, the 3 books can be picked in 84 ways without any restriction.
B. If the dictionary is selected, then we need to choose 2 more books from the remaining 8 books (5 novels
and 3 books of poems):
Total ways = C(8, 2)
Total ways = 28
Therefore, the 3 books can be picked in 28 ways if the dictionary is selected.
C. If 2 novels and 1 book of poems are to be selected, we need to choose 2 novels from the 5 available and
1 book of poems from the 3 available:
Total ways = C(5, 2) * C(3, 1)
Total ways = 10 * 3
Total ways = 30
Therefore, the 3 books can be picked in 30 ways if 2 novels and 1 book of poems are selected.
BAYES’ THEOREM
The Bayes’ theorem is useful in revising the original probability estimates as we gain additional
information about the events or outcomes. The prior probabilities when changed in the light of new
information are called revised or posterior probability. Prior probability is the initial probability based on
the present level of information. Posterior probability is a revised probability based on additional
information.

12 | P a g e
 P ( ¿ A /Bi ) × P(Bi )
P ( B i / A )= k

∑ P( A /B I )× P (B i)
i=1

Suppose there are two urns, marked I and II. Urn I contains 4 red balls and 6 black balls, and Urn II has 3
red balls and 2 black balls. Since one of the Urns is to be selected at random for drawing a ball both Urns
have equal probability of being selected that is
P(x1) = p(x2) = ½ where, Urn I be denoted x1 and Urn II be denoted x2
There are four conditional probabilities from the two outcomes.

Red ball ( Y 1) Black ball ( Y 2 )

4 6
P ( Y 1 / X 1 )= P ( Y 2 / X 1 )=
10 10

3 2
P ( Y 1 / X 2 )= P ( Y 2 / X 2 )=
5 5
From the conditional probability P ( X 1 /Y 2 ) that the ball is selected belongs to Urn I ( X 1) ; given that it is a
black ball ( Y 2 ).
Exercise:
Suppose Urn I contains 4 red, 6 black, 2 white balls; Urn II contains 2 red, 8 black, 4 white balls; and Urn
III contains 6 red, 4 black, and 6 white balls. Further assume that two dies are thrown together. Let Urn
selection be based on the sum of die face points as bellow.
 Urn I is selected for drawing a ball if the sum is equal to 5 or less.
 Urn II is selected for drawing a ball if the sum is equal to 8 or more.
 Urn III is selected for drawing a ball if the sum is equal to 6 or 7.
a) Find the probability that the ball drawn belongs to Urn I when it is known that it is a white ball.
b) Find the probability that the ball drawn belongs to Urn II when it is known that it is a black ball.
c) Find the probability that the ball drawn belongs to Urn III when it is known that it is a red ball.
Solution
There are nine conditional probabilities from the three outcomes.
Red ball ( Y 1) Black ball ( Y 2 ) White ball ( Y 3 )
4 6 2
P ( Y 1 / X 1 )= P ( Y 2 / X 1 )= P (Y 3 / X 1 )=
12 12 12

2 8 4
P ( Y 1 / X 2 )= P ( Y 2 / X 2 )= P (Y 3 / X 2 )=
14 14 14
6 4 6
P (Y 1 / X 3 )= P (Y 2 / X 3 )= P (Y 3 / X 3 )=
16 16 16

Total possible outcome O n = 62 = 36

(1,1) (2,1) (3,1) (4,1) (5,1) (6,1)
(1,2) (2,2) (3,2) (4,2) (5,2) (6,2)
(1,3) (2,3) (3,3) (4,3) (5,3) (6,3)
(1,4) (2,4) (3,4) (4,4) (5,4) (6,4)
(1,5) (2,5) (3,5) (4,5) (5,5) (6,5)
(1,6) (2,6) (3,6) (4,6) (5,6) (6,6)

13 | P a g e
 10 15 11
P ( X 1)= ; P ( X 2 )= ∧P ( X 3 )=
36 36 36

where, Urn I be denoted X 1 ; Urn II be denoted X 2 and Urn III be denoted X 3

a ¿ P ( X 1 /Y 3 ) = k
P ( Y 3 / X 1) × P ( X 1 )
=
( )
2
12
10
×( )
36
=
20
432
=
0.046
=
0.046

( )( )
2 10 4 15 6 11 20 60 66 0.046+0.12+0.11 0.280
∑ P (Y 3 / X i )× P (X i ) 12 × 36 + 14 × 36 + 16 × 36 432 + 504 + 576
i=1

b ¿ P ( X /Y ) =
P ( Y 2 / X 2 ) × P( X 2)
=
( ) 8
14
15
×( )
36
=
120
504
=
0.238
=
0.2

∑ P(Y / X ) × P( X ) ( 12 ) × ( 36 )+ 14 × 36 + 16 × 36 432 + 504 + 576

2 2 k
6 10 8 15 4 11 60 120 44 0.139+ 0.238+0.076 0.4
2 i i
i=1

c ¿ P ( X /Y )=
P ( Y 1 / X 3 ) × P(X 3 )
=
( 6
16 ) 11
×( )
36
=
66
576
=
0.115
=
0.1

∑ P(Y / X )× P(X ) ( 12 )× ( 36 )+ 14 × 36 + 16 × 36 432 + 504 + 576

3 1 k
4 10 2 15 6 11 40 30 66 0.093+0.059+ 0.115 0.2
1 i i
i=1

4.2 PROBABILITY DISTRIBUTION

INTRODUCTION
In many situations, our interest does not lie in the outcomes of an experiment as such; we may find it more
useful to describe a particular property or attribute of the outcomes of an experiment in numerical terms.
For example, out of three births; our interest may be in the matter of the probabilities of the number of
boys. Consider the sample space of 8 equally likely sample points.
GGG GGB GBG BGG
GBB BGB BBG BBB
Now look at the variable “the number of boys out of three births”. This number varies among sample
points in the sample space and can take values 0,1,2,3, and it is random –given to chance.

“A random variable is an uncertain quantity whose value depends on chance.”

A random variable may be…
 Discrete if it takes only a countable number of values. For example, number of dots on two dice,
number of heads in three coin tossing, number of defective items, number of boys in three births
and so on.
 Continuous if it can take on any value in an interval of numbers (i.e. its possible values are
unaccountably infinite). For example, measured data on heights, weights, temperature, and time and
so on.
A random variable has a probability law - a rule that assigns probabilities to different values of the random
variable. This probability law - the probability assignment is called the probability distribution of the
random variable. We usually denote the random variable by X.

14 | P a g e
4.2.1 DISCRETE PROBABILITY DISTRIBUTION
The random variable X denoting “the number of boys out of three births”, we introduced in the introduction
of the lesson, is a discrete random variable; so it will have a discrete probability distribution. It is easy to
visualize that the random variable X is a function of sample space. We can see the correspondence of
sample points with the values of the random variable as follows:

GGG GGB GBG BGG

(X=0) (X=1)
GBB BGB BBG BBB
(X=2) (X=3)

The correspondence between sample points and the value of the random variable allows us to determine the
probability distribution of X as follows:
P(X=0) = 1/8 since one out of 8 equally likely points leads to X = 0
P(X=1) = 3/8 since three out of 8 equally likely points leads to X = 1
P(X=2) = 3/8 since three out of 8 equally likely points leads to X = 2
P(X=3) = 1/8 since one out of 8 equally likely points leads to X = 3
The above probability statement constitute the probability distribution of the random variable X = number
of boys in three births. We may appreciate how this probability law is obtained simply by associating
values of X with sets in the sample space. (For example, the set GGB, GBG, BGG leads to X = 1). We may
write down the probability distribution of X in table format (see Table 4-1)
Table 4-1 Probability Distribution of the Number of Boys out of Three Births
No. of Boys X Probability P(X)
0 1/8
1 3/8
2 3/8
3 1/8
The probability distribution of a discrete random variable X must satisfy the following two conditions:

1. P(X = x) ≥ 0 for all values x

❑
2. ∑ P ( X=x )=1
all x

These conditions must hold because the P(X = x) values are probabilities. The first condition specifies that
all probabilities must be greater than or equal to zero, as we know from Lesson 4.1
For the second condition, we note that for each value x, P(x) = P(X = x) is the probability of the event that
the random variable equals x. Since by definition all x means all the values the random variable X may take,
and since X may take on only one value at a time, the occurrences of these values are mutually exclusive
events, and one of them must take place.
Therefore, the sum of all the probabilities P(X = x) must be 1.00.

Cumulative Distribution Function

The probability distribution of a discrete random variable lists the probabilities of occurrence of different
values of the random variable. We may be interested in cumulative probabilities of the random variable.

15 | P a g e
That is, we may be interested in the probability that the value of the random variable is at most some value
x. This is the sum of all the probabilities of the values i of X that are less than or equal to x.
The cumulative distribution function (also called cumulative probability function) F(X = x) of a discrete
random variable X is
❑
F ( X=x )= p ( X ≤ x ) = ∑ p(i)
alli ≤ x

For example, to find the probability of at most two boys out of three births, we have
❑
F ( X=2 )=P ( X ≤ 2 )= ∑ p(i)
all i ≤2

= P(x=0) + P(x = 1) + P(x = 2)

= 1/8 + 3/8 + 3/8
= 7/8
Discrete probability has three main classifications.
1. Binomial distribution
2. Hyper geometric distribution
3. Poisson distribution

1. Binomial Distribution
Binomial Distribution: It deals with populations whose elements or outcomes can be divided into two
categories with reference to the presence or absence of a particular attribute or characteristic. for example
answers to an exercise may be correct or incorrect, a product may be defective or non defective etc...
Characteristics of a binomial distribution
 It consist of n trials and each trial has only two outcomes, either of which may be designated as a
success or failures.
 The probability of a success p remains the same in all trials. Consequently, the probability of a
failure q = (1- p) also remains the same in all trials.
 The number of successes in n trials can be expressed by the random variable X that assumes discrete
values from 0 to n.
 Repeated trials are independent since no definite pattern is involved in the occurrence of either of
the two outcomes in successive trials.

Binomial Distribution(b): b (x; n, p) = nCx . px . qn-x or nCx . px . (1-p)n-x

n!
Where: nCx =
x !(n−x )!
μ=np
δ ¿ √ npq
δ = npq
2

n! = is read as n factorial = n(n-1) (n-2) (n-3)......1

n = number of trials
p = probability of success
q = probability of failures
x = exact number of success in a trials (0, 1, 2, 3......n)
C = is the symbol for combination
μ=¿mean of binomial distribution
16 | P a g e
δ=¿ Standard deviation of binomial distribution
2
δ =¿Variance of binomial distribution

Example 11: toss a coin 4 times; what is the probability of getting:

a) exactly two heads
b) exactly four heads
c) at most three heads
Answer
To calculate the probabilities for each scenario, we need to use the concept of binomial probability.

Let's define:
- n = 4 (number of coin tosses)
- x = number of heads
- p = probability of getting a head in a single toss (0.5 for a fair coin)
- q = probability of getting a tail in a single toss (1 - p)

A. Probability of getting exactly two heads:

P(X = 2) = C(n, x) * p^x * q^(n-x)
P(X = 2) = C(4, 2) * (0.5)^2 * (0.5)^2
P(X = 2) = 6 * 0.25 * 0.25
P(X = 2) = 0.375

Therefore, the probability of getting exactly two heads when tossing a coin 4 times is 0.375 or 37.5%.

B. Probability of getting exactly four heads:

P(X = 4) = C(4, 4) * (0.5)^4 * (0.5)^0
P(X = 4) = 1 * 0.0625 * 1
P(X = 4) = 0.0625

Therefore, the probability of getting exactly four heads when tossing a coin 4 times is 0.0625 or 6.25%.

C. Probability of getting at most three heads:

P(at most 3 heads) = P(X = 0) + P(X = 1) + P(X = 2) + P(X = 3)
P(at most 3 heads) = C(4, 0) * (0.5)^0 * (0.5)^4 + C(4, 1) * (0.5)^1 * (0.5)^3 + C(4, 2) * (0.5)^2 * (0.5)^2 +
C(4, 3) * (0.5)^3 * (0.5)^1
P(at most 3 heads) = 1 * 1 * 0.0625 + 4 * 0.5 * 0.125 + 6 * 0.25 * 0.25 + 4 * 0.125 * 0.5
P(at most 3 heads) = 0.0625 + 0.25 + 0.375 + 0.25
P(at most 3 heads) = 0.9375

Therefore, the probability of getting at most three heads when tossing a coin 4 times is 0.9375 or 93.75%.
Example 12: In the throw of a fair die, point 5 coming up is considered a success with probability = 1/6.
The probability of not getting point 5, a failure is q (1-p) = 5/6. If the die is throw 4 times. Find all the
binomial probability?
Answer
To calculate the binomial probabilities for each scenario, we need to use the binomial probability formula:

P(X = x) = C(n, x) * p^x * q^(n-x)

17 | P a g e
where:
- n = 4 (number of times the die is thrown)
- x = number of successes (getting point 5)
- p = probability of success (getting point 5) = 1/6
- q = probability of failure (not getting point 5) = 5/6

Let's calculate each scenario:

A. Probability of getting exactly two successes (point 5):

P(X = 2) = C(4, 2) * (1/6)^2 * (5/6)^(4-2)
P(X = 2) = 6 * (1/36) * (25/36)
P(X = 2) = 150 / 1296
P(X = 2) ≈ 0.11574 or approximately 11.57%

B. Probability of getting exactly four successes (point 5):

P(X = 4) = C(4, 4) * (1/6)^4 * (5/6)^(4-4)
P(X = 4) = 1 * (1/1296) * 1
P(X = 4) = 1 / 1296
P(X = 4) ≈ 0.00077 or approximately 0.077%

C. Probability of getting at most three successes (point 5):

P(at most 3 successes) = P(X = 0) + P(X = 1) + P(X = 2) + P(X = 3)
P(at most 3 successes) = C(4, 0) * (1/6)^0 * (5/6)^4 + C(4, 1) * (1/6)^1 * (5/6)^3 + C(4, 2) * (1/6)^2 * (5/6)^2 + C(4, 3) * (1/6)^3 * (5/6)^1
P(at most 3 successes) = 1 * (625/1296) + 4 * (5/216) + 6 * (25/1296) + 4 * (125/7776)
P(at most 3 successes) ≈ 0.51775 or approximately 51.77%

Therefore, the binomial probabilities for the given scenarios are:

A. P(X = 2) ≈ 0.11574 or approximately 11.57%
B. P(X = 4) ≈ 0.00077 or approximately 0.077%
C. P(at most 3 successes) ≈ 0.51775 or approximately 51.77%

Example 13: Suppose 60% of Management students pass Statistics for Management I final examination
and there were a total of 50 students, find
a) the expected value of the number of success
b) standard deviation and variance
c) To find the expected value, standard deviation, and variance of the number of successes (students
passing the exam), we can use the binomial distribution formula:

1. Expected Value (Mean):

The expected value of a binomial distribution is given by:
E(X) = n * p
where:
- n = total number of trials (students) = 50
- p = probability of success (students passing) = 0.60

E(X) = 50 * 0.60
E(X) = 30

Therefore, the expected value (mean) of the number of students passing the exam is 30.
18 | P a g e
2. Variance:
The variance of a binomial distribution is given by:
Var(X) = n * p * q
where:
- n = total number of trials (students) = 50
- p = probability of success (students passing) = 0.60
- q = probability of failure (students failing) = 1 - p = 1 - 0.60 = 0.40

Var(X) = 50 * 0.60 * 0.40

Var(X) = 12

Therefore, the variance of the number of students passing the exam is 12.

3. Standard Deviation:
The standard deviation is the square root of the variance:
SD(X) = √Var(X)
SD(X) = √12
SD(X) ≈ 3.46

Therefore, the standard deviation of the number of students passing the exam is approximately 3.46.

In summary:
- Expected Value (Mean): 30
- Variance: 12
- Standard Deviation: Approximately 3.46

2. Hyper geometric Distribution

Hyper geometric Distribution: deals with situations where a random sample of size n drawn without
replacement from a finite population, and the resultant outcomes are classified into two categories
(successes and failures) according to some characteristics or attributes.

Characteristics of hyper geometric distribution

i. A random sample of size n is selected from the finite population of N items without replacement; so
that the probability of getting a success is not the same in each trials.
ii. K out of N items comprising the population are classified as success and (N-K) items as failures.
Hyper geometric Distribution(h): h(x; N, n, k) = h(x) = (kCx) (N-k)Cn-x
NCn
K
μ = n( ¿
N

K N −K N −n
δ = n(
2
¿( ¿( ¿
N N N−1
Where; N = the size of the population
K = the number of successes in the population
n = the size of the sample or the number of trials
x = the number of success of interest, it may be 0, 1, 2, 3,..........n

19 | P a g e
Example 14: Assume that an Urn contains 6 red balls and 4 black balls. If a sample of 4 balls is drawn
from the Urn without replacement. find:
a) the probability of getting 2 successes out of 6 balls
b) the probability of all values of hyper geometric variables
c) the mean and the variance of hyper geometric distribution
Answer
A. Probability of getting 2 successes out of 6 balls:
To calculate the probability of getting 2 red balls (successes) out of 4 balls drawn without replacement, we
can use the hypergeometric distribution formula:

P(X = k) = (C(n, k) * C(N-n, n-k)) / C(N, n)

where:
- P(X = k) is the probability of getting exactly k successes
- C(n, k) is the number of ways to choose k items from a set of n items (combination)
- N is the total number of balls in the urn (6 red + 4 black = 10)
- n is the number of balls drawn (4)
- k is the number of red balls drawn (2)

P(X = 2) = (C(6, 2) * C(4, 2)) / C(10, 4)

P(X = 2) = (15 * 6) / 210
P(X = 2) = 90 / 210
P(X = 2) = 0.4286 or approximately 0.43
Therefore, the probability of getting exactly 2 red balls out of 4 drawn is approximately 0.43.

B. Probability of all values of the hypergeometric variable:

The hypergeometric distribution represents the probability distribution for the number of successes in a
sample drawn without replacement. To find the probabilities for all possible values (0 to 4), you would
calculate P(X = 0), P(X = 1), P(X = 2), P(X = 3), and P(X = 4) using the same formula as above.

C. Mean and Variance of the hypergeometric distribution:

The mean (expected value) and variance of the hypergeometric distribution can be calculated as follows:

Mean (Expected Value):

μ = n * (N / (N + m))
where:
- μ is the mean
- N is the total number of red balls in the urn (6)
- m is the total number of black balls in the urn (4)
- n is the number of balls drawn (4)

μ = 4 * (6 / 10)
μ = 2.4
Therefore, the mean of the hypergeometric distribution is 2.4.

Variance:
Var(X) = n * [(N / (N + m)) * ((m / (N + m)) * ((N - n) / (N + m - 1))]
where:

20 | P a g e
- Var(X) is the variance
- N, m, and n are as defined above

Var(X) = 4 * [(6 / 10) * (4 / 10) * (2 / 9)]

Var(X) = 0.64

Therefore, the variance of the hypergeometric distribution is 0.64.

Example 15: Suppose 50 play stations were manufactured during the week. Forty operated perfectly and
ten had at least one defect. A sample of 5 is selected at random without replacement. What is the
probability that 4 of the 5 will operate perfectly?

Answer
To calculate the probability that 4 out of the 5 selected play stations will operate perfectly, we can use the
hypergeometric distribution formula:

P(X = k) = (C(A, k) * C(B, n-k)) / C(N, n)

where:
- P(X = k) is the probability of getting exactly k successes
- C(A, k) is the number of ways to choose k items from a set of A items (combination)
- C(B, n-k) is the number of ways to choose (n-k) items from a set of B items
- N is the total number of play stations manufactured during the week (50)
- A is the number of play stations that operated perfectly (40)
- B is the number of play stations with defects (10)
- n is the number of play stations selected in the sample (5)
- k is the number of play stations that operate perfectly in the sample (4)

Now, let's calculate the probability:

P(X = 4) = (C(40, 4) * C(10, 1)) / C(50, 5)

P(X = 4) = (91,390 * 10) / 2,118,760
P(X = 4) = 913,900 / 2,118,760
P(X = 4) ≈ 0.431 or approximately 0.43

Therefore, the probability that 4 out of the 5 selected play stations will operate perfectly is approximately
0.43.

3. Poisson Distribution
Poisson Distribution: refers to the problem situation in which occurrence an event and counting the
number of times the event occurs during the specified time intervals.
 It is the number of occurrences of an event and not the non- occurrences in a given situations that is
of interest.
 the events must be random and independent of each other.
x −μ
μ e
Poisson Distribution = p(x) =
x!
Where, μ=¿is the average number of occurrence(successes) per unit of time
21 | P a g e
 e = is the base of natural logarithms and is equal to 2.718282
x = is the number of occurrence (success)
Example 16: Assume that on an average 3 persons enter the bank for service every 10 minutes. What is the
probability that exactly 5 customers will enter the bank in a given 10 minutes period, assuming that the
process can be described by the Poisson distribution.

Answer
To calculate the probability that exactly 5 customers will enter the bank in a given 10-minute period using
the Poisson distribution, we need to use the formula:

P(X = k) = (e^(-λ) * λ^k) / k!

where:
- P(X = k) is the probability of exactly k events occurring
- e is the base of the natural logarithm (approximately equal to 2.71828)
- λ (lambda) is the average rate of events occurring in a given time period (3 customers every 10 minutes)
- k is the number of events we are interested in (5 customers)

First, we need to calculate λ for a 10-minute period:

λ = 3 customers / 10 minutes = 0.3 customers per minute

Now, we can plug these values into the formula:

P(X = 5) = (e^(-0.3) * 0.3^5) / 5!

P(X = 5) = (0.740818 * 0.00243) / 120
P(X = 5) ≈ 0.000014 or approximately 0.0014%

Therefore, the probability that exactly 5 customers will enter the bank in a given 10-minute period,
assuming a Poisson distribution, is approximately 0.0014%.

Example 17: Customers arrive at a photocopying machine at an average rate of two every 10 minutes. the
number of arrival is distributed according to a Poisson distribution. What is the probability that:
a) there will be no arrivals during any period of 10 minutes.
b) there will be exactly one arrival during this time period.
c) there will be more than two arrivals during this period
Answer
To calculate the probabilities for the different scenarios, we will use the Poisson distribution formula:

P(X = k) = (e^(-λ) * λ^k) / k!

where:
- P(X = k) is the probability of exactly k events occurring
- e is the base of the natural logarithm (approximately equal to 2.71828)
- λ (lambda) is the average rate of events occurring in a given time period (2 customers every 10 minutes)
- k is the number of events we are interested in

Given that λ = 2 customers / 10 minutes = 0.2 customers per minute, we can now calculate the probabilities
for each scenario:

22 | P a g e
1. Probability of no arrivals during any period of 10 minutes (k = 0):
P(X = 0) = (e^(-0.2) * 0.2^0) / 0!
P(X = 0) = e^(-0.2) ≈ 0.8187 or approximately 81.87%

2. Probability of exactly one arrival during this time period (k = 1):

P(X = 1) = (e^(-0.2) * 0.2^1) / 1!
P(X = 1) = 0.2 * e^(-0.2) ≈ 0.1637 or approximately 16.37%

3. Probability of more than two arrivals during this period:

P(more than two arrivals) = 1 - P(0 arrivals) - P(1 arrival)
P(more than two arrivals) = 1 - e^(-0.2) - 0.2 * e^(-0.2)
P(more than two arrivals) ≈ 1 - 0.8187 - 0.1637 ≈ 0.0176 or approximately 1.76%

Therefore, the probabilities are:

- Probability of no arrivals during any period of 10 minutes: approximately 81.87%
- Probability of exactly one arrival during this time period: approximately 16.37%
- Probability of more than two arrivals during this period: approximately 1.76%

4.2.2 Continuous probability Distribution (Normal Distribution)

The normal distribution is a continuous distribution and plays a very important role in statistical theory and
practice particularly in the areas of statistical quality control.

Characteristics of the normal curve

1. the normal curve is not a single curve representing only one continuous distribution. It represents a
family of normal curve.
2. the normal curve is completely determine by the values of mean and standard deviation which are
its two parameters.
3. the curve has a single peak at the center of the distribution. It has the same value for mean, median
and mode.
4. the height of the curve declines as we go in either directions from the mean, but never touches the
base so that, the tails of the curve on both sides of the mean extend indefinitely.
5. being bell-shaped, the normal curve is perfectly symmetrical about the vertical axis through the
mean. As a result 50% of the area lies to the rights of the mean and the other 50% to its left.
6. no matter what values of mean and standard deviation are for a normal probability distribution, the
total area under the normal curve is 1.
The resultant Z values express the distance between mean and the x values measured interms of standard
deviation.

x−μ
Z= δ or x = μ ± zδ
Z score is positive for values which are to the right of the mean and negative to the left of the mean.

Three different ways of measuring the area under the normal curve
1. About 68% of the area under the normal curve is within ±1 standard deviation from the mean.
2. About 95.45% of the area under the normal curve is within ±2 standard deviation from the mean.
3. About 99.75% of the area under the normal curve is within ±3 standard deviation from the mean.
TABLE 1 Normal Curve Areas
23 | P a g e
The entries in the body of the table
correspond to the area shaded under
the normal curve.

Finding the areas when the score is known

Example 18: The IQ scores of students is normally distributed with mean of 120 and standard deviation of
20. What proportion of students have:
a) An IQ between 100 and 130
b) An IQ above 140
c) An IQ below 150
d) An IQ between 140 and 150

24 | P a g e
Finding the score when the area is known
Example 19: Taking the above mean = 120 and standard deviation = 20 and answer the following
questions:
a) find the score so that 20% of the students have an IQ above this score
b) What are the limits within the central 50% of the score lies?
c) find the score so that 70% of the students have an IQ below this score.
Answer
Given mean = 120 and standard deviation = 20, we can solve the following questions:

1. Find the score so that 20% of the students have an IQ above this score:
To find this score, we need to find the z-score corresponding to the 80th percentile (since we are looking
for the score above which 20% of the students lie).

Using the z-score formula:

z = (X - μ) / σ
We look up the z-score corresponding to the 80th percentile in the standard normal distribution table or use
a calculator. The z-score corresponding to the 80th percentile is approximately 0.84.

Now, we can find the IQ score (X) using:

0.84 = (X - 120) / 20
X - 120 = 0.84 * 20
X - 120 = 16.8
X ≈ 136.8

Therefore, the score so that 20% of the students have an IQ above this score is approximately 136.8.

2. Find the limits within which the central 50% of the scores lie:
The central 50% of the scores corresponds to the middle 50% of the distribution. This means that 25% of
the scores lie below the lower limit and 25% lie above the upper limit.

To find these limits, we need to find the z-scores corresponding to the 25th and 75th percentiles,
respectively.

For the lower limit:

z_lower = (X_lower - μ) / σ
Using z-table, z_lower ≈ -0.6745
-0.6745 = (X_lower - 120) / 20
X_lower ≈ 106.51

For the upper limit:

z_upper = (X_upper - μ) / σ
Using z-table, z_upper ≈ 0.6745
0.6745 = (X_upper - 120) / 20
X_upper ≈ 133.49

Therefore, the limits within which the central 50% of the scores lie are approximately between 106.51 and
133.49.

25 | P a g e
3. Find the score so that 70% of the students have an IQ below this score:
To find this score, we need to find the z-score corresponding to the 70th percentile.

Using z-table or calculator, the z-score corresponding to the 70th percentile is approximately 0.5244.

Now, we can find the IQ score (X) using:

0.5244 = (X - 120) / 20
X - 120 = 0.5244 * 20
X ≈ 130.49

Therefore, the score so that 70% of the students have an IQ below this score is approximately 130.49.

Exercise: The final examination scores in Statistics are normally distributed with an average score of 70
and variance of 25.
a) If the lowest passing grade is 58, what percentage of the class is failing?
b) If the professor gives the grades on a curve and everybody getting 82 or above gets a grade of A,
then what percentage of students get A grade?
c) If the highest 80% of the class are to pass the course, what is the lowest passing score?
d) What should the score be so that only 15% of the students get a score higher than this?

Answer
Given average score = 70 and variance = 25, we can solve the following questions:

1. What percentage of the class is failing if the lowest passing grade is 58?
To find the percentage of the class failing, we need to find the z-score corresponding to a score of 58.

z = (X - μ) / σ
z = (58 - 70) / √25
z = -12 / 5
z = -2.4

Using a standard normal distribution table or calculator, the percentage of students failing (below a score of
58) is approximately 0.0082 or 0.82%.

2. What percentage of students get an A grade if the cutoff is 82 or above?

To find the percentage of students getting an A grade, we need to find the z-score corresponding to a score
of 82.

z = (X - μ) / σ
z = (82 - 70) / √25
z = 12 / 5
z = 2.4

The percentage of students getting an A grade (above a score of 82) is approximately 0.9918 or 99.18%.

3. What is the lowest passing score if the highest 80% of the class are to pass?
To find the lowest passing score for the top 80% of the class, we need to find the z-score corresponding to
the 80th percentile.

26 | P a g e
Using a standard normal distribution table or calculator, the z-score corresponding to the 80th percentile is
approximately 0.8416.

Now, we can find the score (X) using:

0.8416 = (X - 70) / √25
X - 70 = 0.8416 * 5
X ≈ 74.21

Therefore, the lowest passing score for the top 80% of the class is approximately 74.21.

4. What should the score be so that only 15% of the students get a score higher than this?
To find this score, we need to find the z-score corresponding to the 85th percentile (since we want only
15% of students to have a higher score).

Using a standard normal distribution table or calculator, the z-score corresponding to the 85th percentile is
approximately 1.0364.

Now, we can find the score (X) using:

1.0364 = (X - 70) / √25
X - 70 = 1.0364 * 5
X ≈ 75.18

Therefore, the score should be approximately 75.18 so that only 15% of students get a score higher than
this.

To solve these questions, we can use the properties of the normal distribution. We'll assume that the
final examination scores are normally distributed with a mean (average) score of 70 and a variance of
25.

Given:
- Mean (μ) = 70
- Variance (σ^2) = 25
- Lowest passing grade = 58

1. What percentage of the class is failing?

To find the percentage of students failing (scoring less than 58), we can use the Z-score formula for the
standard normal distribution:

Z = (X - μ) / σ

Where:
Z = standard score
X = individual score
μ = mean
σ = standard deviation (square root of variance)

We want to find the probability of getting a score less than 58, so we'll calculate the Z-score for 58:

27 | P a g e
 Z = (58 - 70) / √25
= -12 / 5
= -2.4

Using a standard normal distribution table or calculator, we can find the area to the left of Z = -2.4 which
gives us the percentage of students failing. This percentage will be very close to 0% since -2.4 represents a
very low score compared to the mean.

2. What percentage of students get an A grade (82 or above)?

We can use the same approach, finding the Z-score for 82 and then calculating the percentage of students
with a score greater than or equal to 82.

Z = (82 - 70) / √25

= 12 / 5
= 2.4

Using the standard normal distribution table or calculator, we find the area to the right of Z = 2.4, which
gives us the percentage of students getting a grade of A.

3. What is the lowest passing score for the highest 80% of the class to pass the course?
To find the lowest passing score for the highest 80% of the class, we need to find the Z-score
corresponding to the 80th percentile. In other words, we want to find the score (X) for which 80% of the
class scored lower than that.

Using the Z-score table or calculator, we find the Z-score that corresponds to the 80th percentile. Then we
can use the Z-score formula to solve for X:

X=μ+Z*σ
= 70 + Z * √25

4. What score should be such that only 15% of the students get a score higher than this?
This can be rephrased as finding the score (X) for which 15% of the class scored higher. Similar to the
previous question, we'll find the Z-score corresponding to the 85th percentile (since 100% - 15% = 85%)
and use the Z-score formula to solve for X:

X=μ+Z*σ
= 70 + Z * √25

I hope this helps! Let me know if you need assistance with any specific calculation.

28 | P a g e