STATISTICAL THEORY

LECTURE 6

MARY ANN YEBOAH

1
PROBABILITY

Under probability to be able to combine two or more events there is the need to apply two
important rules that is the Addition rule and the multiplication rule. The addition rule deals
with the situation where we have the events to be mutually exclusive or not mutually
exclusive such that if for example we want to find the probability of the union between A and
B then the relationship will be as follows

P( A  B) = P( A) + P(B) − P( A  B) – When events are not mutually exclusive

P( A  B) = P( A) + P(B) – When events are mutually exclusive

The Multiplication Rule

The multiplication rule is applied when it is necessary to compute the probability if both
events A and B will occur at the same time. The multiplication rule is different if the two
events are independent as against the two events being not independent. There are two
aspects to this rule, the conditional probability and the independent events.

Conditional Probability (multiplication rule for events that are not independent)

In many situations, a manager may know the outcome of an event that has already occurred
and may want to know the chances of a second event occurring based upon the knowledge of
the outcome of the earlier event.

Let us assume that a new brand of toothpaste is being introduced in the market. Based on the
study of competitive market the manufacturer has some idea about the chances of its success
Now, he introduces the product in a few selected stores in a few selected areas before
marketing it nationality. A highly positive response from the test – market area will improve
his confidence about the success of his brand nationally. Accordingly, the manufacturer’s
assessment of high probability of sales for his brand would be on condition that he gets a
positive response from the test market.
In short we want to calculate the probability that an event A will occur conditioned on the
fact that an event B has already occurred. We call this probability the conditional probability
of A given B and denote it by P (A/B). The probability P (A/B) is defined as

P( A  B )
P( A / B ) = P (B )  0
P (B )
P( A  B) denotes the probability that both events occur at the same time. P( A  B) is called
the joint probability of A and B.

2
Example 1
Find the probability of picking a picture card from a pack of 52 cards given that the card is a
heart.

P (Picture card/ Heart) = P(picture card and a heart)

P (Heart)

3
= 52 = 3
13 13
52

Example 2
A die is rolled and the number that came up is larger than 4. Find the probability that the
outcome is an even number given that it is larger than 4.

Solution
Let A = even numbers
B = larger than 4

A = {2, 4, 6} A B = 6
B = {5, 6}
1
P( A  B ) 1
P (A/B) = = 6=
P (B ) 2 2
6
Example 3
A supply of 10 light bulbs contains 2 defective bulbs. If the bulb is picked up in a random
manner in succession without replacement, what is the probability that the first two bulbs are
good?
Solution

G be for non-defective bulbs Defective bulbs = 2

D be for defective bulbs Non defective bulbs = 8

P (G  G) = P (G) X P G ( G)
8 7 28
 =
10 9 45

Independent events

Two events are said to be independent if the occurrence of one has no influence on the
occurrence of the other. In other words the occurrence of A does not affect the occurrence of
B if A and B are independent events. For example, if two fair coins are tossed, then the result

3
of one toss is totally independent of the result of other toss. The probability that a head will
be the outcome of anyone toss will always be ½ irrespective of whatever the outcome is of
the other toss. Hence these two events are independent. When events A and B are
independent, then P (A/B) = P (A) That is, the probability of Event A is the same whether or
not events A & B is given by P (A  B) = P (A)  P (B).

Example 1
Use the following probabilities to determine whether or not events A and B are independent
events.

1 1 1
(a) P (A) = , P (B) = and P (A  B) =
4 7 11

(b) P (A) = 0.7, P (B) = 0.5 and P (A  B) = 0.21

(c) P (A) = 22% P (B) = 10% and P (A  B) = 32%

(d) P (A) = 0.3 P (B) = 0.8 and P (A  B) = 0.24

Solution
1 1 1
(a) P (A) • P (B) =  = . It is given that P (A  B) = 1⁄11 this means that
4 7 28
P (A  B)  P (A) • P (B), therefore events A and B are not independent.

(b) P (A)  P (B) = 0.7 X 0.5 = 0.21. It is given that P (A  B) = 0.21, this means that
P (A  B) = P (A) • P (B) Hence events A & B are independent events.

(c) P (A) • P (B) = 0.22 x 0.1 = 0.022; it is given that P (A  B) = 0.32, this implies that
P (A  B)  P (A) • P (B), therefore events A and B are not independent.

(c) P (A) • P (B) = 0.3 x 0.8 = 0.24. It is given that P (A  B) = 0.24, this implies that
P (A  B) = P (A) • P (B), hence events A & B are independent.

Example 2
A fair due and a fair coin are tossed at the same time. What is the probability that the die
shows a 2 and the coin shows a head?

Solution
Let M be the event that the die shows a 2
N be the event that the coin shows a head
Then P (A) =1⁄6 and P (B) = 1⁄12

4
The occurrence of a number 2 has no effect on the occurrence of a head, so it is clear that
events A and B are independent.

This P (A  B) = P (A) x P (B)

= 1⁄6 x 1⁄2 = 1⁄12

Example 3
A bowl contains 6 red apples and 4 green apples. An apple is drawn at random from the bowl,
and then a second apple is drawn with replacement of the 1st apple. Find the probability that
1st is red and 2nd is green.

Solution
Let R for red apples and G for Green apples, n = 10
P (R) = 6⁄10 P (G) = 4⁄10
P (R  G) = P (R) x P (G)

= 6⁄10 x 4⁄10 =
24
100

Example 4
A crate contains 5 white eggs and 9 brown eggs. What is the probability that the first egg
drawn is white and the second is brown, given that the selections are made (a) with
replacement (b) without replacement?

Solution
Let W denote the event that a white egg is drawn
And B denote the event that a brown egg is drawn
We know that there are 14 eggs on the crate altogether.
Therefore at the 1st draw P (W) = 5⁄14
The draw is with replacement. This means that the 1 st egg drawn is replaced before the brown
egg is drawn next.
Therefore at the second draw P (B) = 9⁄14
We can therefore see that the two events are independent.

a. P (W  B) = P (W) x P (B)
5 9 45
= 14 x14 = 196

b. At the 1st draw P (W) = 5⁄14

The draw is without replacement. That is the white egg drawn is not replaced before the
brown pencil is drawn next. So at the 2rd draw, we have 13 eggs left out of which 9 are
brown. Therefore P (𝐵⁄𝑊 ) = 9⁄13

5
 Note that the 2nd draw is affected by the 1 st, hence the conditional probability
P (𝐵⁄𝑊)
5 9 45
P (𝑊  𝐵) = P (W) x P (𝐵⁄𝑊) =  =
14 13 182

Bayes Rule / Theorem

In this section, we will learn how to use the Baye’s rule, which is a well-known result in
probability theory. The rule is named after an 18th century Presbyterian minister called
Reverend Thomas Bayes. He attempted to develop a formula to arrive at the probability that
God does exist based on evidence that was available to him on earth. Today, we use the rule
to compute a conditional probability, when the information given does not allow us to apply
the conditional multiplication rule of probability directly.
In solving problems arising in probability theory using the event approach, it is sometimes
essential to view the sample space as a union of mutually exclusive events. The baye’s
theorem can be used in such instance.

Conditions that requires the use of Baye’s rule

1. The experiment conducted should result in one of n mutually exclusive events A 1, A2,.., An
such that the sample space S, is given by S = { A1  A2  …..  An}

2. It is given that an event B has occurred and that P (B)  0

3. To Find the probability that one of the events A1, A2,…….An will occur given that event B
has occurred, i.e. Is P (Ai/ B) , i = 1, 2, ………, n.

We now state the rule as follows

P (Ai / B) = P (Ai) P (Ai)
P (B/A1) P(A1) + P (B/A2)P (A2) +…… + P (B/An) P (An)

Anyone of the probabilities P(A1), P(A2),..., P(An) in the rule above is called a prior
probability. It is prior because their values are assigned before real data are obtained. The
probabilities P (Ai /E) are called posterior probabilities and the sum in the denominator is
called total probability.

Laws of Total Probability

Suppose A1, A2,…,An are n mutually exclusive events and collectively exhaustive so that A 1
 A2  ……..  An = S where P(Ai) > 0, i = 1,2,……….,n and A  Aj  0 for some i & j
then for any event B

P(B ) =  P( Ai )P(B / Ai )

6
Example 1

Suppose P (A1) = 0.20 P (A2) = 0.40 P (A3) = 0.40

P (B/A1) = 0.25 P (B/A2) = 0.05 and P (B/A3) = 0.10.

Use Bayes rule to find P (A1/B)

Solution

P (A1/B) = P (B/A1) P (A1)

P (B/A1) P(A1) + P (B/A2)P (A2) +…… + P (B/A3) P (A3)

= (0.25) (0.20)
(0.25) (0.20) + (0.05) (0.40) + (0.1) (0.4)

= (0.25) (0.20)
0.05 + 0.02 + 0.04

= 0.05
0.11
= 0.455

Example 2

The probability that a professional account officer will pass her professional exam is 5⁄9. If
she passes, the probability that she will be promoted is 3⁄4. Given that she is promoted, what
is the probability? She has passed her professional exams?

S – pass F – fail M – promoted N – not promoted

P (S) = 5⁄9 P (F) = 1 - 5⁄9 = 4⁄9 P (M/S) = ¾ P (𝑀⁄𝐹 ) = 1 -3⁄4 = 1⁄4

P (𝑆⁄𝑀) = P (M/S) P (S)

P (𝑀⁄𝑆) P (S) + P (𝑀⁄𝐹 ) P (F)

= 3⁄ X 5⁄
4 9

3⁄ X 5⁄ + 1⁄ X 4⁄
4 9 4 9

7
 15
15
= 36 = 36 = 15
15 4 19 19
+ 36
36 36

Example 3
It is given that only 60% of the new brand of powdered milk in Nestle passed the quality test
on the spot. Of the milk that passed 80% wholly prepared and of those that failed 20% were
accurately prepared. What is the probability that a tin of milk that passed the test was wholly
prepared?

Solution

P = passing F – failing W – wholly prepared

P (W/P) = 0.80 P (W/F) = 0.20 P (P) = 0.60 P (F) = 1 – 0.6 = 0.4

P (P/W) = P (W/P) • P (P)

P (W/P) • P (P) + P (W/F) • P (F)

= 0.80 x 0.6
(0.80 x 0.6) + (0.2 x 0.4)

= 0.48
0.48 + 0.08

= 0.48
0.56

= 0.86

Example 4
A probability that a construction job will be finished on time is 3⁄5 and the probability that
there will be no strike is 2⁄3 and the probability that the job will be finished on time given
that there is no strike is 4⁄5. What is the probability that
(a) The job will be finished on time and there will be no strike
(b) There will have been no strike given that the job is finished on time?

8
Solution

T = on time SN = no strike S= Strike

P (T) =3⁄5 P(SN) = 2⁄3 P (𝑇⁄𝑆𝑁) = 4⁄5
P (S) = 1 – 2⁄3 = 1⁄3 P (𝑇⁄𝑆) = 1 - 4⁄5 = 1⁄5

(a) P (T  SN) = P (𝑇⁄𝑆𝑁). P (SN)

= 4⁄5 x 2⁄3 = 8⁄15

(b) P (𝑆𝑁⁄𝑇) = P (T/SN). P (SN)

P (T/SN). P (SN) + P (T/S) . P (S)

= 4⁄ x 2⁄
5 3

4⁄ x 2⁄ + 1⁄ x 1⁄
5 3 5 3

= 8⁄
15

8⁄ + 1⁄
15 15

= 8⁄
15

9⁄
15

= 8⁄
9
Combinations

Combination is a counting technique. A combination is the selection of objects without

regard to order. The order of items is necessary in the permutation technique which is the
other counting technique. In many case, however the order is unimportant. For example, the
probability of any two heads out of three tosses would be different than having two heads and
a tail in that order.

According the number of combinations of n district items taken x at a time without any given
order is given by

n!
Simply written as n C r or (𝑛𝑟) or nCr
r!(n − r )!

(For r = 0 or r = n we define 0! = 1) (0<r < n)

9
 Pr
n
Cr = n

r!
This gives the number of combinations of n elements taking r at a time

Example 1

Find 10C3

Solution
10! 10! 10 x 9 x 5 x 7 !
10C3 = = =
(10−3)!3! 7!x 3! 7!x 3!

720
= = 120
6

Example 2

A committee of ten members of parliament (MPs) has been selected to investigate the ethical
conduct of the ministers. A sub – committee of four MPs is to be selected out of ten MPs to
investigate one minister. Determine the number of ways in which any four members can be
selected out of these ten.

Solution

Since the order of such selection is unimportant, the number of ways of choosing the sub –
committee is given by

n 10
10!
Cr = C4 =
(10−3)!4!

10! 10 x 9 x 8 x 7 x 6! 5040
= = = = 210
6!x 4! 6!x 24 24

Example 3

How many railways are needed to connect 15 villages if there is to be exactly one railway
between any two villages?

Solution

N = 15 and r = 2
15!
Hence 15C2 =
(15−2)!2!

15 x 14 x 13! 210
= = = 105 railways.
13!x 2! 2

10
Example 4

The chairman of the board of directors of a company wishes to set up a small finance
committee comprising three directors from a group of seven. Calculate the possible
alternative ways in he can make this selection.

Solution

This is a combination question as the committee order of the members is not important.

N = 7 and r = 3

n 7
7!
Cr = C3 =
(7−3)!3!

7 x 6 x 5 x 4!
=
4!x 6

= 35 ways

Example 5

A school basketball squad for the inter – school competition has ten players. The coach must
select a team for the 1st tournament. How many different teams of five players can be
constituted for this tournament?

Solution

Here, we are not interested in the positions each of the five players in the team will take. It is
therefore a problem of combination hence

n 10
10!
Cr = C5 =
(10−5)!5!
10!
=
5!x 5!
10 x 5 x 8 x 7 x 6 x 5!
=
5!x 5!
10 x 9 x 8 x 7 x 6
=
5x4x3x2x1
= 252 teams

Combinations and products

It is possible to also determine the number of ways specified subsets can be selected from two
or more given sets using a counting principle. For two sets, the principle states that
If a finite set A contains r elements and another

11
 Finite set B contains s elements then A x B contains rs elements.

This principle can be extends to three or more events.

Example 1
In how many ways can a set of four mathematics books and three biology books be selected
from a set of six mathematics and seven biology books?

Solution
Selection of 4 and out of 6 mathematics books
6 7!
C4 = 4!3! = 35

Applying the counting principle stated above.

The totals election = 15 x 35 = 525ways

Example 2
The under writing syndicate is to be formed fro, a group of insurance companies, each of
which is classified either as type A or type B. There are 6 type A and 8 type B insurance
companies. In how many ways can a syndicate of 6 companies be formed if it must consist of
3 companies of type A and 3 of type B.?

Solution
Selection for type A n=6 r=3

6
6! 6 x 5 x 4 x 3!
C3 = = = 20
3!3! 3!x 6

Selection for type B n=8 r=3

8
8! 8 x 7 x 6 x 5!
C3 = = = 56
5!3! 5!x 6
Applying the counting principle = 20 x 56
= 1120 ways.
Example 3
Part A and B of a test contain 10 and 6 questions respectively. In how many ways can a
student select 5 questions from part A and 3 questions from part B?
Solution

10 10!
From A n = 10 r=5 C5 = = 252
5!x 5!

12
 6 6!
From B n=6 r=3 C3 = = 20
3!x 3!

252 x 20 = 5040 ways

Combinations in probability
We may find it useful to apply the combinations technique to solve some problems in
probability especially those involving selection of objects without replacement

Example 1
Two balls are drawn at random from a bag containing 12 purple and 10 yellow balls. What is
the probability that

(a) Both are purple (b) one is purple and the other is yellow

Solution
The bag contains 22 balls

Number of ways of drawing 2 balls from the bag 22C2

The bag contains 12 purple balls
Number of ways of drawing 2 purple balls is 12C2
Let R denote the events that both are purple then

(a) P (K) = Number of favourable events = 12C2 = 66

22
Total number of events C2 231

(b) The bag contains 12 purple and 10 yellow balls

Number of ways of drawing 1 purple 12C1
Number of ways of drawing 1 yellow 10C1

Let M denote the event that one ball is purple and the then other is yellow
P(M) = Number of favourable events
Total number of events
12
= C2 x 10C1
22
C2

= 12 x 10
13
 231

= 0.519

Example 2

Three pencils are drawn at random from a school containing 15 and 12 red pencils. What is
the probability that

(a) All three are green

(b) Non is green
(c) One is green and the two are red

Solution

a. Let G be for Green and R for red

455
P (3G) = 15
C3 = 15 X 14 X 13 = 27 X 26 X 25 X 24 =
2925
27
C3 6 6

15
C3 455 35
(b) 1− 27
=1 − =
C3 2925 45

(c) P (G  2R) = 15C1 X 12C2

27
C3
15  66 990 22
= = =
2925 2925 65

14