QMS 100: Mathematics &

Statistics
COMPULSORY COURSE IN: HRM

Kimaro_Novat_MU-MCC 1
 PART A
MATHEMATICS

Kimaro_Novat_MU-MCC 2
 BASIC CONCEPTS
The role of Mathematics and Statistics in HR.
• HR is not just about controlling a work force and
sorting out personale problems if and when they occur.
• HR should be responsible for analyzing all aspects of
personale activity and data and making sure that the
company they are working benefits from their
analysis, and that means using math.

Kimaro_Novat_MU-MCC 3
 BASIC CONCEPTS
• HR need to use math to define standard productivity.
• It also needs math to track and use data so workforce
information is known.
• It also needs math to perform complex analyses that
will give insight in to management initiatives and
programs that have a financial impact on the
performance of a business.

Kimaro_Novat_MU-MCC 4
 BASIC CONCEPTS
• HR need to use math so that they can analyze long
term financial impacts of any suggested changes
within the business and how they may impact on the
workforce and on management so that accurate
forecasts can be given as to the outcome.
• Math and statistics are used in developing and
implementing machine learning techniques for HR
purposes.
Kimaro_Novat_MU-MCC 5
 BASIC CONCEPTS
• Predictive analytics can be used for predicting the
success of a candidate before recruiting.
• Also, some companies are working on technology that
understands certain employee trends and predict if
they are planning to quit anytime soon.

Kimaro_Novat_MU-MCC 6
 BASIC CONCEPTS
Sets and set operation

Kimaro_Novat_MU-MCC 7
 BASIC CONCEPTS
Sets and Set Operations.
• A set is a collection of well defined objects.
• The objects in the collection are called elements of the
set.
• Sets are often specified with curly brace notation
i.e. ,.

Kimaro_Novat_MU-MCC 8
 BASIC CONCEPTS
• For example, consider the collection of all integers,
...,−4, −3, −2, −1, 0, 1, 2, 3, 4,...
• Collection of world continents;
𝐴𝑓𝑟𝑖𝑐𝑎, 𝑁. 𝐴𝑚𝑒𝑟𝑖𝑐𝑎, 𝑆. 𝐴𝑚𝑒𝑟𝑖𝑐𝑎, 𝐴𝑠𝑖𝑎, 𝐸𝑢𝑟𝑜𝑝𝑒, 𝐴𝑢𝑠𝑡𝑟𝑎𝑙𝑖𝑎 𝑎𝑛𝑑 𝐴𝑛𝑡𝑎𝑟𝑐𝑡𝑖𝑐𝑎
• A set is called an infinite set if it has infinitely many
elements; otherwise it is called a finite set.

Kimaro_Novat_MU-MCC 9
 BASIC CONCEPTS
• The null set, or empty set, denoted ∅ , is the set
with no members.
• We often let uppercase letters stand for sets , e.g.
𝐴 = 2,4,6,8 .
• If we write 2 ∈ 𝐴 means 2 belongs to set A and
if we write 7 ∉ 𝐴 means 7 does not belong to set
A.
Kimaro_Novat_MU-MCC 10
 BASIC CONCEPTS
Ways of Describing Sets
a) A set can be described by listing (Roaster form) all
of its elements.
• For example, S = { 1, 3, 5, 7, 9 },which we read as ‘S
is the set whose elements are 1, 3, 5, 7 and 9’.
• The five elements of the set are separated by commas,
and the list is enclosed between curly brackets.

Kimaro_Novat_MU-MCC 11
 BASIC CONCEPTS
(b) A set can also be described by writing a
description of its elements between curly
brackets.
• E.g.: S = { odd whole numbers less than 10 },
• which we read as ‘S is the set of odd whole
numbers less than 10’.

Kimaro_Novat_MU-MCC 12
 BASIC CONCEPTS
(c) Use set builder notation.
• This specifies the sets using a predicate/formula
to indicate the attributes of the elements of the
set.
• E.g.: the set of even integers is 𝑥: 𝑥 = 2𝑛, 𝑛 ∈

Kimaro_Novat_MU-MCC 13
 BASIC CONCEPTS
Questions:
1. Write the following sets in the roaster form.
(i) A = {x | x is a positive integer less than 10 and
2𝑥 – 1 is an odd number}.
2
(ii) C = 𝑥 : 𝑥 + 7𝑥 – 8 = 0, 𝑥 ∈ ℝ}.

Kimaro_Novat_MU-MCC 14
 BASIC CONCEPTS
(iii) If Y = {𝑥 | 𝑥 is a positive factor of the number
2𝑝−1 (2𝑝 – 1), where 2𝑝 – 1 is a prime number}.
2. Write the set in set builder form.
𝐴 = 𝐴𝑙𝑙 𝑒𝑣𝑒𝑛 𝑝𝑜𝑠𝑖𝑡𝑖𝑣𝑒 𝑖𝑛𝑡𝑒𝑔𝑒𝑟𝑠
3. Write 0,1,2 … 10 in set –builder notation
4.Write out the set 𝑥: 𝑥 𝑖𝑠 𝑎𝑛 𝑖𝑛𝑡𝑒𝑔𝑒𝑟 𝑙𝑒𝑠𝑠 𝑡ℎ𝑎𝑛 4
in roster notation.
Kimaro_Novat_MU-MCC 15
 BASIC CONCEPTS
Relationship Between Sets.
• A set A is a subset of a set B, denoted as 𝐴 ⊆ 𝐵,
if and if every element of A is also an element of
B.
• If 𝐴 ⊆ 𝐵 but A ≠ 𝐵 then we say A is a proper
subset of B and denoted as 𝐴 ⊂ 𝐵.

Kimaro_Novat_MU-MCC 16
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 17
 BASIC CONCEPTS
Question: State whether it is true or false.

Kimaro_Novat_MU-MCC 18
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 19
 BASIC CONCEPTS

• Two sets are equal if they contain exactly the same

elements. Thus 2,4,6,8 = 4,2,8,6 .

Kimaro_Novat_MU-MCC 20
 BASIC CONCEPTS
Set Operations.

Kimaro_Novat_MU-MCC 21
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 22
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 23
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 24
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 25
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 26
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 27
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 28
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 29
 BASIC CONCEPTS
The Complement of A is denoted as 𝐴 or 𝐴𝑐 or 𝐴′ and is
defined as:
𝐴 = 𝑥 ∈ 𝑈: 𝑥 ∉ 𝐴

For example: if 𝐴 = 1, 2, 3 and 𝑈 = −1,0, 1, 2, 3 then,

𝐴 = −1,0
Kimaro_Novat_MU-MCC 30
 BASIC CONCEPTS
• Graphical representations of sets are called Venn
diagrams, after their inventor, British logician John
Venn, 1834–1923.

Kimaro_Novat_MU-MCC 31
 BASIC CONCEPTS
Questions:
1.Use a Venn Diagram to show the following sets.
a) 𝐴 ∪ 𝐵 ∪ 𝐶
b) 𝐴 ∩ 𝐵 ∩ 𝐶
c) 𝐴 − 𝐵
d) 𝐴 ∩ 𝐵 ∩ 𝐶 ′
e) 𝐴 ∪ 𝐵 ∩ 𝐶
Kimaro_Novat_MU-MCC 32
 BASIC CONCEPTS
2. Suppose sets A and B are in a universal set U.
a) Draw Venn diagrams for 𝐴 ∪ 𝐵and 𝐴 ∩ 𝐵.
b) Based on your drawings, do you think it’s true that
𝐴 ∪ 𝐵 = 𝐴 ∩ 𝐵?

Kimaro_Novat_MU-MCC 33
 BASIC CONCEPTS
3.

Kimaro_Novat_MU-MCC 34
 BASIC CONCEPTS
4. What does the shaded region in each figure
below represent in set notation?

Kimaro_Novat_MU-MCC 35
 BASIC CONCEPTS
5. In a survey of 130 people, the following data were collected: 106
people subscribed to the newspaper, 29 people subscribed to
magazines, and 17 people were members of a mail CD club.
Seventeen subscribed to both the newspaper and the magazines, 5
people subscribed to magazines and were members of a CD club,
and 10 people subscribed to the newspaper and were members of a
mail CD club. Three people
subscribed to both the newspaper and magazines and were
members of a mail CD club. Make and fill in a Venn diagram to
illustrate this situation.
Kimaro_Novat_MU-MCC 36
 BASIC CONCEPTS
Laws of Set Operations.

Kimaro_Novat_MU-MCC 37
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 38
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 39
 BASIC CONCEPTS
• Questions.
1. Use the laws of set operation to show that;
(a)𝐴 ∩ 𝐵 = 𝐵 − 𝐵 − 𝐴
(b)𝐴 ∪ 𝐵 − 𝐴 = 𝐴 ∪ 𝐵
(c) 𝐴 − 𝐶 ∩ 𝐶 − 𝐵 = ∅
2. Simplify using properties of set operations.
a) 𝐴 ∩ 𝐴 ∪ 𝐵 ′
b) 𝐵 − 𝐵 − 𝐴
Kimaro_Novat_MU-MCC 40
 BASIC CONCEPTS
3. A total of 58 teens attended a sports camp to train in
at least one of three sports: swimming, cycling, and
running.
 35 trained in swimming, 32 trained in cycling, and 38
trained in running.
9 trained in swimming and cycling, but not in running.

Kimaro_Novat_MU-MCC 41
 BASIC CONCEPTS
11 trained in cycling and running, but not in
swimming.
13 trained in swimming and running, but not in
cycling.
• A triathlon consists of swimming, cycling, and
running. How many teens might be training for the
upcoming triathlon?

Kimaro_Novat_MU-MCC 42
 BASIC CONCEPTS
4. Out of 130 students of a certain University, 10 of
them study PUB 065 and QMS 100 while 20 study
neither of the two subjects. Those who study PUB 065
alone are three times as many as those who study QMS
100 only. Required
a) Summary the information using Venn-diagram.
b) How many students study PUB 065?

Kimaro_Novat_MU-MCC 43
BASIC CONCEPTS

Kimaro_Novat_MU-MCC 44
 EQUATIONS AND INEQUALITIES
The Concept of a Variable.
• A variable is a quantity that may change within the
context of a mathematical problem or experiment.
• Typically, we use a single letter to represent a variable.
• The letters x, y, and z are common generic symbols
used for variables.
• For instance t can represent time, p for price (variable).
Kimaro_Novat_MU-MCC 45
EQUATIONS AND INEQUALITIES

Kimaro_Novat_MU-MCC 46
 EQUATIONS AND INEQUALITIES
Independent and Dependent Variable
• In any given model or equation, there are two types of
variables:
a) Independent variables - The values that can be changed
or controlled in a given model or equation. They provide
the "input" which is modified by the model to change the
"output.“
b) Dependent variables - The values that result from the
independent variables.
Kimaro_Novat_MU-MCC 47
 EQUATIONS AND INEQUALITIES
• For example:
• A scientist studies how many days people can
eat soup until they get sick. The independent
variable is the number of days of consuming
soup. The dependent variable is the onset of
illness.

Kimaro_Novat_MU-MCC 48
 EQUATIONS AND INEQUALITIES
• Let’s say 𝑦 is the number of kilometers you’ve driven
in a vehicle and let’s say 𝑥 is the amount of fuel your
vehicle uses in litres.
• So the independent variable is 𝑥, and the dependent
variable is 𝑦.
• Mathematically:
𝑦=𝑓 𝑥
• This means 𝑦 depends on 𝑥.
Kimaro_Novat_MU-MCC 49
 EQUATIONS AND INEQUALITIES
Mathematical equations.
• If two expressions are connected by equality symbol
i.e.,= the equation is formed.
• Examples of equations;
i. 2𝑥 + 12 = 3,
3
ii. 𝑥 − 8 = 3𝑥,
iii. 16𝑏 = 8, etc.
Kimaro_Novat_MU-MCC 50
 EQUATIONS AND INEQUALITIES
The linear Equation
• The equation in the form of 𝑎𝑥 + 𝑏𝑦 = 𝑐 where
𝑎, 𝑏 𝑎𝑛𝑑 𝑐 are constants is called a linear equation.
• If the linear equation is written in the form of 𝑦 =
𝑚𝑥 + 𝑐 then it is called a linear function.
• If one of the variable is zero ,then we have one
variable linear equation.

Kimaro_Novat_MU-MCC 51
 EQUATIONS AND INEQUALITIES
• Find the values of unknown in the following linear
equations:
3
a) 4 𝑚 = 13 − 6𝑚
b) 𝑥 + 0.4𝑥 = 3.5
c) −3 + 8𝑥 = 4𝑥 + 3
d) 6𝑡 + 10 = 9𝑡 − 2
3
e) 𝑦 − 12 = 3𝑦
4
2𝑥−1 3𝑥 5
f) 3
−
4
=
6

Kimaro_Novat_MU-MCC 52
 EQUATIONS AND INEQUALITIES
Quadratic equations.
• The polynomial with highest degree of two is
called a quadratic equation.
• Its general form is given as 𝑎𝑥 2 + 𝑏𝑥 + 𝑐 = 0
where 𝑎 ≠ 0 and a, b and c are all constants and
ℝ.

Kimaro_Novat_MU-MCC 53
 EQUATIONS AND INEQUALITIES
Examples of quadratic equations
2
1. 3𝑥 + 8𝑥 + 7 = 0,
2. −3𝑥 2 + 2𝑥 + 6 = 0
2
3. 𝑥 + 16 = 0
2
4. 𝑦 + 3𝑦 = 0

Kimaro_Novat_MU-MCC 54
 EQUATIONS AND INEQUALITIES
Methods of solving quadratic equations:
1. Graphical method(the solutions are obtained where
the curve crosses the x-axis)
2. Algebraic methods (Factorization, Completing the
square, Inspection and general formula).

Kimaro_Novat_MU-MCC 55
 EQUATIONS AND INEQUALITIES
• The general quadratic solution is given by
−𝑏± 𝑏2 −4𝑎𝑐
•𝑥 =
2𝑎
2
• If 𝑏 = 4𝑎𝑐 then a quadratic has equal real roots.
• If 𝑏 2 > 4𝑎𝑐 then a quadratic has distinct real roots.
• If 𝑏 2 < 4𝑎𝑐 then a quadratic has complex conjugate
roots.

Kimaro_Novat_MU-MCC 56
 EQUATIONS AND INEQUALITIES
• If 𝛼, 𝑎𝑛𝑑 𝛽 are roots of a quadratic equation \
𝑎𝑥 2 + 𝑏𝑥 + 𝑐 = 0 then 𝑥 − 𝛼, 𝑥 − 𝛽 are the
factors.
• Multiplying the factors then;
𝑥 2 − 𝛼 + 𝛽 𝑥 + 𝛼𝛽 = 0
• Comparing with the general form then
𝑏 𝑐
𝛼+𝛽 = − and 𝛼𝛽 =
𝑎 𝑎
Kimaro_Novat_MU-MCC 57
 EQUATIONS AND INEQUALITIES
Example: Solve the quadratic equation;
𝑥 2 − 6𝑥 + 8 = 0
By general formula

− −6 ± −6 2 − 4 1 8
𝑥=
2×1
6±2
𝑥=
2
𝑥 = 4 or 2
Kimaro_Novat_MU-MCC 58
 EQUATIONS AND INEQUALITIES
By splitting the middle term
2
𝑥 − 6𝑥 + 8 = 0
𝑥 2 − 4𝑥 − 2𝑥 + 8 = 0 −4 𝑎𝑛𝑑 − 2 𝑎𝑟𝑒 𝑓𝑎𝑐𝑡𝑜𝑟𝑠
𝑥 2 − 4𝑥 − 2𝑥 + 8 = 0
𝑥 𝑥−4 −2 𝑥−4 =0
𝑥−2 𝑥−4 =0
Either 𝑥 − 2 = 0 or 𝑥 − 4 = 0
Then 𝑥 = 2 or 𝑥 = 4
Kimaro_Novat_MU-MCC 59
 EQUATIONS AND INEQUALITIES
By completing the squares Method.
𝑥 2 − 6𝑥 + 8 = 0
𝑥 2 − 6𝑥 + 8 − 8 = 0 − 8
𝑥 2 − 6𝑥 = −8
Dividing the middle term(coefficient) by 2 , squaring and adding the
results on both sides.
𝑥 2 − 6𝑥 + (−3)2 = −8 + (−3)2
𝑥−3 2 =1
𝑥 − 3 = ±1
𝑥 =3±1
𝑥 = 2 𝑜𝑟 4
Kimaro_Novat_MU-MCC 60
 EQUATIONS AND INEQUALITIES
Questions: Use either of the methods above to find the
solutions of the following quadratic equations.
1. 3𝑡 2 − 14𝑡 + 8 = 0
3 4−𝑥
2. 𝑥−1 𝑥+3+
𝑥−1
=
𝑥−1
𝑥−1
3. 2
6𝑥 + 9𝑥 − 6 = 0
4. 𝑥 2 + 2𝑥 − 15 = 0
5. 𝑥 4 − 10𝑥 2 + 9 = 0
1 2 1
6. 𝑦−
𝑦
− 10 𝑦 −
𝑦
+ 24 = 0
7. 𝑥 2 + 12 − 𝑥 2 + 5=1

Kimaro_Novat_MU-MCC 61
 EQUATIONS AND INEQUALITIES
1. The production (p) of a firm for a commodity is 𝑃 = 15𝐾 +
2𝐿𝐾 − 𝐿2 − 0.5𝐾 2 , 𝑤ℎ𝑒𝑟𝑒 L and K denote labor and capital
respectively. The relationship between L and K is 𝐿 + 𝐾 = 4.If
production is 11.5 units, find labor units.
2. For what value (or values) of m will the following quadratic
equation have equal roots?
𝑚 + 1 𝑥 2 + 2 𝑚 + 3 𝑥 + 2𝑚 + 3 = 0
3. Find the market equilibrium price and the quantity if the demand
equation is 𝑝 − 3𝑞 = 22 and the supply equation is 𝑞2 + 2𝑝 + 4𝑞 =
100 where p is the price and q is the quantity of the commodity. Find
the total revenue at market equilibrium price.

Kimaro_Novat_MU-MCC 62
 EQUATIONS AND INEQUALITIES
Simultaneous Equations
• For several equations with more than one variable,
then we can be solve them simultaneously by either of
the following methods.
Elimination method.
Substitution method.
Matrix method.
Graphical method.
Kimaro_Novat_MU-MCC 63
 EQUATIONS AND INEQUALITIES
Use either of the methods above to find the value of
unknowns in:
𝑥𝑦 = 6
1.
𝑥 − 5 = −𝑦
Solution: By substitution method
𝑥𝑦 = 6 … … … … … … … … … … … … . . 𝑒𝑞𝑛(𝑖)
𝑥 − 5 = −𝑦 … … … … … … … … … 𝑒𝑞𝑛(𝑖𝑖)
From 𝑒𝑞𝑛(𝑖𝑖) 𝑥 = 5 − 𝑦 … … … … … … … … 𝑒𝑞𝑛(𝑖𝑖𝑖)
Substituting into 𝑒𝑞𝑛(𝑖𝑖𝑖) then

Kimaro_Novat_MU-MCC 64
EQUATIONS AND INEQUALITIES
𝑦 5−𝑦 =6
2
5𝑦 − 𝑦 − 6 = 0
𝑦 2 − 5𝑦 + 6 = 0 which quadratic
2
𝑦 − 2𝑦 − 3𝑦 + 6 = 0
𝑦 𝑦 − 2 − 3 𝑦 − 2 =0
𝑦−3 𝑦−2 =0
𝑦 = 3 𝑜𝑟 2

Kimaro_Novat_MU-MCC 65
 EQUATIONS AND INEQUALITIES
Problems:
4𝑥 + 2𝑦 = 8
1.
6𝑥 − 3𝑦 = 16
2. Solve the following simultaneous equations
𝑦 − 1 = 3𝑥
𝑦 + 𝑥 2 = 7 + 2𝑥
3. A trader gains one third of the cost price as profit on a product and
one fourth of the cost price as profit on other product. Total profit
earned on these two products is $43. The sum of the cost prices of
two products is $150. Find the cost price of each product.

Kimaro_Novat_MU-MCC 66
 EQUATIONS AND INEQUALITIES
𝑥 2 = 𝑦 2 − 14
4.
𝑥 = 𝑦 2 − 16

−5𝑥 = 6𝑦
5.
3𝑥 + 6𝑦 = 16

−𝑥 + 5𝑦 + 𝑧 = 4
6. 4𝑥 − 8𝑦 = 0
3𝑥 + 7𝑦 − 2𝑧 = 6

Kimaro_Novat_MU-MCC 67
 EQUATIONS AND INEQUALITIES
7.Find the market equilibrium price and the
quantity if the demand equation is 𝑝 − 3𝑞 = 22
and the supply equation is 𝑞2 + 2𝑝 + 4𝑞 = 100
where p is the price and q is the quantity of the
commodity. Find the total revenue at market
equilibrium price.

Kimaro_Novat_MU-MCC 68
 EQUATIONS AND INEQUALITIES
8. The sum of the squares of two positive integers is 41
and their product is 20. Find the numbers.
9. Mr. KAJUNA invests some amount in deposit A and
some amount in deposit B. The total money invested is
$2500. He gets 10% income on deposit A and 20%
income on deposit B. If the total income earned be
$380, find the amount invested in A and B separately

Kimaro_Novat_MU-MCC 69
 EQUATIONS AND INEQUALITIES
Inequalities.
• If the symbols rather than equality joins two
expressions the result is the inequality such
symbols include; <, >, ≤, 𝑎𝑛𝑑 ≥.
2
• Examples of inequalities; 3𝑥 − 6 <0 , 2𝑦 +
9 > 12, etc.

Kimaro_Novat_MU-MCC 70
 EQUATIONS AND INEQUALITIES
• Properties of inequalities:

Kimaro_Novat_MU-MCC 71
 EQUATIONS AND INEQUALITIES
• Examples.
7−2𝑥
1. Solve the inequality −3 < ≤4
3
Solution.
Multiplying by 3; −9 < 7 − 2𝑥 ≤ 12 then
−16 < −2𝑥 ≤ 5 Dividing by -2
−5
8>𝑥≥
2
Kimaro_Novat_MU-MCC 72
 EQUATIONS AND INEQUALITIES
2.

Kimaro_Novat_MU-MCC 73
 EQUATIONS AND INEQUALITIES
2 7
• Solving: 𝑥 = or −
3 2
• Using the number line to check for the solution regions.

Kimaro_Novat_MU-MCC 74
 EQUATIONS AND INEQUALITIES
• Questions
• Solve the following inequalities
1 2
1. 𝑥−2
>
𝑥+3
2𝑥−4
2. −4 <≤7
3
3. −1 ≤ 2𝑥 + 5 < 7

Kimaro_Novat_MU-MCC 75
EQUATIONS AND INEQUALITIES
4
4. ≤ −2
3𝑥−2
2
5. 4𝑥 − 4𝑥 + 1 ≥ 0
6. (𝑥 + 1)(𝑥 − 2) ≥ (𝑥 − 4)(𝑥 + 6)

Kimaro_Novat_MU-MCC 76
 EQUATIONS AND INEQUALITIES
7.

Kimaro_Novat_MU-MCC 77
 FUNCTIONS AND GRAPHS
Concept of a function and representation by an
equation.
• Function is a special kind of relation.
• A relation in which each 𝑥-coordinate is matched with
only one 𝑦-coordinate is said to describe 𝑦 as a function
of 𝑥.
• This means that there cannot be any repeated 𝑥 −values
with different 𝑦 −values.
• One way to demonstrate the meaning of this definition is
by using arrow diagrams.
Kimaro_Novat_MU-MCC 78
FUNCTIONS AND GRAPHS

Kimaro_Novat_MU-MCC 79
 FUNCTIONS AND GRAPHS
• Which of the following relations describe 𝑦 as a
function of 𝑥?
𝑅1 = (−2,1), (1,3), (1,4), (3, −1)}
𝑅2 = (−2,1), (1,3), (2,3), (3, −1)}
• 𝑅1 reveals that the 𝑥 −coordinate 1 is matched
with two different 𝑦 −coordinates: namely 3 and
4
Kimaro_Novat_MU-MCC 80
FUNCTIONS AND GRAPHS
• Hence in 𝑅1 , 𝑦 is not a function of 𝑥.
• In 𝑅2 , every 𝑥 −coordinate occurs only once
which means each 𝑥 −coordinate has only one
corresponding 𝑦 −coordinate.
• So, 𝑅2 does represent y as a function of 𝑥.

Kimaro_Novat_MU-MCC 81
 FUNCTIONS AND GRAPHS
• The Vertical Line Test: A set of points in the plane represents 𝑦 as a
function of 𝑥 if and only if no two points lie on the same vertical line.
• Example: Use the Vertical Line Test to determine which of the
following relations describes 𝑦 as a function of 𝑥.

Kimaro_Novat_MU-MCC 82
 FUNCTIONS AND GRAPHS
• Solution.
• Looking at the graph of 𝑅, we can easily imagine
a vertical line crossing the graph more than once.
Hence, 𝑅 does not represent 𝑦 as a function of 𝑥.
• However, in the graph of 𝑆, every vertical line
crosses the graph at most once, so 𝑆 does
represent 𝑦 as a function of 𝑥.
Kimaro_Novat_MU-MCC 83
 FUNCTIONS AND GRAPHS
• If 𝑥 the input and 𝑦 the output. In function
notation we write
𝑦 = 𝑓(𝑥).
• ‘𝑓(𝑥)’, read ‘𝑓 𝑜𝑓 𝑥. ’
• Since 𝑦 depends on 𝑥 , then 𝑥 is called the
independent variable and 𝑦 the dependent
variable.
Kimaro_Novat_MU-MCC 84
FUNCTIONS AND GRAPHS
• There are four common ways in which functions
are presented and used: Verbally (by a
description in words), numerically (by a table of
values),Visually (by a graph), and algebraically
(by a formula/equation as above).

Kimaro_Novat_MU-MCC 85
 FUNCTIONS AND GRAPHS
Questions: Determine which equations represent 𝑦
as a function of 𝑥.
1. 𝑦 = 2𝑥 + 4
2. 𝑥 3 + 𝑦 2 = 1
3 2
3. 𝑦 + 𝑥 = 1
2
4. 𝑥 𝑦 = 1 − 3𝑦
5. 2𝑥𝑦 = 4
Kimaro_Novat_MU-MCC 86
 FUNCTIONS AND GRAPHS
• Questions: For the following functions;
1) If 𝑓 𝑥 = 𝑥 4 + 𝑥 2 − 2, find 𝑓 𝑥 − 1
3𝑥+1
2) If 𝑦 = 𝑓 𝑥 = , prove that 𝑓 𝑦 = 𝑥
5𝑥−3
2 1 1
3) If 𝑓 𝑥 = 𝑥 − 2 , show that 𝑓 𝑥 + 𝑓( )=0
𝑥 𝑥
𝑥−1 𝑥−1 −1
4) If 𝑓 𝑥 = , show that 𝑓 =
𝑥+1 𝑥+1 𝑥
5) If 𝑓 𝑥 = 𝑥 2 , find 𝑓 𝜋 , 𝑓 4 , 𝑓 6
6) If 𝑓 𝑥 = 𝑎𝑥 + 𝑏, find the value of a and b given that 𝑓 1 = 12
and 𝑓 2 = 8

Kimaro_Novat_MU-MCC 87
 FUNCTIONS AND GRAPHS
The domain and range of a function.
• Suppose 𝑅 is a relation which describes 𝑦 as a function of 𝑥.
• The set of the 𝑥 −coordinates of the points in 𝑅 is called the domain
of 𝑅.
• The set of the 𝑦 −coordinates of the points in 𝑅 is called the range of
R.
Example 1: Find the domain and range of the function
𝐹 = (−3, 2), (0, 1), (4, 2), (5, 2)}

Kimaro_Novat_MU-MCC 88
 FUNCTIONS AND GRAPHS
• Domain of F is the set of the 𝑥 −coordinates =
−3, 0, 4, 5 and Range of F is the set of the
𝑦 −coordinates= 1, 2 .
Example 2: Find, algebraically, the domain and the
range of each of the following functions.
a) 𝑦 = 𝜋𝑥 2
1
b) 𝑦 = 𝑥−4
1
c) 𝑦 = 2 + 𝑥
Kimaro_Novat_MU-MCC 89
 FUNCTIONS AND GRAPHS
Questions: Find the domain and range of the
following functions.
1. 𝑓 𝑥 = 𝑥
𝑥
2. 𝑔 𝑥 = 𝑥−1
2
3. ℎ 𝑥 = 𝑥 − 4x

Kimaro_Novat_MU-MCC 90
FUNCTIONS AND GRAPHS
1.The population of a certain County can be
150𝑡
modeled by the function 𝑃(𝑡) = , where
𝑡+15
𝑡 represents the number of years since 1803. Find
and interpret 𝑃(0) and 𝑃(205). Discuss with
your classmates what the applied domain and
range of 𝑃 should be.

Kimaro_Novat_MU-MCC 91
 FUNCTIONS AND GRAPHS
Types of functions.
• Functions are classified by the type of
mathematical equation which represents their
relationship. There are several types of functions
which includes but not limited to:
1.Transcendental functions. (all exponential,
logarithm, trig functions)
Kimaro_Novat_MU-MCC 92
 FUNCTIONS AND GRAPHS
1.Even and odd functions.e.g.
2.Composite functions.e.g.𝑦 = 𝑥 + 1 5
3.Periodic functions. E.g., 𝑠𝑖𝑛 𝑥 + 2𝜋 =𝑠𝑖𝑛𝑥 of
all 𝑥
4. Polynomial functions (Linear, quadratic,
cubic,…)

Kimaro_Novat_MU-MCC 93
 FUNCTIONS AND GRAPHS
6. Rational function.
7. Many –One function.
8. Absolute functions.
9. One valued function(one-one function) e.g. 𝑦 = 𝑥
10. Explicit functions. e.g., 𝑦 = 5𝑥 +8
2 3
11. Implicit functions. e.g., 𝑥 − 5𝑦 + 6𝑦𝑥 − 8 = 0

Kimaro_Novat_MU-MCC 94
 FUNCTIONS AND GRAPHS
Graphs of functions.
1. The graph of linear function.
• If the linear equation is written in the form of 𝑦 =
𝑚𝑥 + 𝑐 then it is called a linear function.
• Where 𝑚 is called a gradient or slope and 𝑚 is 𝑦-
intercept.
• The graph can be drawn by using either intercepts or
table of values methods.
Kimaro_Novat_MU-MCC 95
 FUNCTIONS AND GRAPHS
Example 1: Draw the graph of the linear equation
given by 𝑥 + 𝑦 = 3 ,hence determine the
intercepts.
Solution: Re-writing: y = −x + 3 then
by intercepts method
Let x = 0 then y –intercept= 3
y = 0 then x-intercept= 3
Kimaro_Novat_MU-MCC 96
 FUNCTIONS AND GRAPHS
• The graph of 𝑥 + 𝑦 = 3 is then given by;
𝑦

→𝑥+𝑦=3
𝑥
0 3

Kimaro_Novat_MU-MCC 97
 FUNCTIONS AND GRAPHS
For each of the following linear equations, determine
their slopes and intercepts then sketch their graphs on
the coordinates’ plane
1. 3𝑥 − 5𝑦 = 0,
2. 𝑦 = −3𝑥 − 6,
3. 𝑦 = −4𝑥 + 8,
𝑥 𝑦
4. 2 + 3 = 1,
5. 2𝑥 = 3𝑦 − 12
Kimaro_Novat_MU-MCC 98
 FUNCTIONS AND GRAPHS
2. The Graph of Quadratic function.
• Its general form is given as f 𝑥 = 𝑎𝑥 2 + 𝑏𝑥 + 𝑐
where 𝑎 ≠ 0 and a, b and c are constant and real.
• The graphs of quadratic equation depends on the
value of a constant 𝑎 such that;
• When 𝑎 < 0 open down ward.
• When 𝑎 > 0 and upward .
Kimaro_Novat_MU-MCC 99
 FUNCTIONS AND GRAPHS
• The nature of graph of a quadratic when 𝑎 > 0.
𝑦

𝑥
0

Kimaro_Novat_MU-MCC 100
 FUNCTIONS AND GRAPHS
• The nature of graph of a quadratic when 𝑎 < 0
𝑦

𝑥
0

Kimaro_Novat_MU-MCC 101
 FUNCTIONS AND GRAPHS
• Without the table of values, the graph quadratic
is drawn by:
1. Identifying intercepts
2. Finding the turning point by either calculus or
𝑏 4𝑎𝑐−𝑏2
the by the formula − ,
2𝑎 4𝑎

Kimaro_Novat_MU-MCC 102
 FUNCTIONS AND GRAPHS
• Example. Draw the graph of each of the
following functions.
2
1) 𝑓 𝑥 = 𝑥 − 5𝑥 + 6
2) 𝑓 𝑥 = −𝑥 2 + 4𝑥 + 12
2
3) 𝑓 𝑥 = 𝑥 − 2𝑥 − 8

Kimaro_Novat_MU-MCC 103
 FUNCTIONS AND GRAPHS
3. The Graph of Cubic functions.
• General form is 𝑓 𝑥 = 𝑎𝑥 3 +𝑏𝑥 2 + 𝑐𝑥 + 𝑑 for a, b, c and d ∈ ℝ
and 𝑎 ≠ 0
• Use the table of values to draw the graphs of the following.
1) 𝑦 = 𝑥 3
2) 𝑦 = 𝑥 − 1 3
3) 𝑦 = 𝑥 + 2 (𝑥 2 − 4)

Kimaro_Novat_MU-MCC 104
 DIFFERENTIAL CALCULUS
• Differentiation is the process of finding out the derivatives of
continuous function.
• A derivative is the limit of the ratio of the increment in the function
corresponding to a small increment in the argument as the later tends
to zero.
Δ𝑦 𝛿𝑦
• Or is the incremental ratio of dependent variable 𝑦 with respect
Δ𝑥 𝛿𝑥
to the independent variable 𝑥.
• If 𝑥 is very small (approaching or tending to zero) the ratio then is
written as

Kimaro_Novat_MU-MCC 105
 DIFFERENTIAL CALCULUS
𝛿𝑦 𝑑𝑦
• lim =
𝛿𝑥→0 𝛿𝑥 𝑑𝑥
𝑑𝑦
• Thus is the rate of change in 𝑦 with respect to
𝑑𝑥
a change in 𝑥 and is called the derivative of a
function 𝑦 w.r.t.𝑥 (differential co-efficient).
• Other notation of differential co-efficient is 𝑦 ′ or
′ 𝑑
𝑓 𝑥 or 𝐷𝑦 or 𝑓 𝑥
𝑑𝑥
Kimaro_Novat_MU-MCC 106
 DIFFERENTIAL CALCULUS
Gradient of a function.
• Let 𝑦 = 𝑓(𝑥) be a general function.
• To get the gradient/Slope of the function at a given point P(𝑥, 𝑦)
consider the sketch below.
𝑦
𝑦 = 𝑓(𝑥)
𝑓(𝑥 + ℎ) Q

𝑓(𝑥)
𝑃(𝑥, 𝑦)
0 𝑥
𝑥 𝑥+ℎ

Kimaro_Novat_MU-MCC 107
 DIFFERENTIAL CALCULUS
• The slope of the function at point P is equal to
the slope of the tangent line.
• To get the slope of the tangent , we find the slope
of secant line and as h becomes small then slope
of secant equals the slope of tangent.
• Gradient of the secant line PQ is given by:
Δ𝑦 𝑓 𝑥+ℎ −𝑓(𝑥)
•𝑚 = =
Δ𝑥 𝑥+ℎ−𝑥
Kimaro_Novat_MU-MCC 108
 DIFFERENTIAL CALCULUS
• Introducing the limit
Δ𝑦 𝑑𝑦 𝑓 𝑥+ℎ − 𝑓 𝑥
•𝑚= lim = =lim
∆𝑥→0 Δ𝑥 𝑑𝑥 ℎ→0 ℎ
• This is the slope of the tangent at P.
• At the point P the slope of the curve is equal to slope of the tangent
line.
• The slope of the function 𝑦 = 𝑓(𝑥) at a point is now given by:
′ Δ𝑦 𝑑𝑦 𝑓 𝑥+ℎ − 𝑓 𝑥
•𝑓 𝑥 = lim = =lim
∆𝑥→0 Δ𝑥 𝑑𝑥 ℎ→0 ℎ

Kimaro_Novat_MU-MCC 109
 DIFFERENTIAL CALCULUS
• Example 1. Find the slope of the curve give by 𝑦 = 𝑥 2 − 5𝑥 at
(2, −6)
• Solution: Let f 𝑥 = 𝑦 = 𝑥 2 − 5𝑥
• f 𝑥 + ℎ = 𝑥 + ℎ 2 − 5(𝑥 + ℎ)
𝑓 𝑥+ℎ − 𝑓 𝑥
• 𝑓′ 𝑥 = lim
ℎ→0 ℎ
𝑥+ℎ 2 −5(𝑥+ℎ) − 𝑥 2 −5𝑥
• 𝑓 ′ 𝑥 = lim
ℎ→0 ℎ
𝑥 2 +2𝑥ℎ+ℎ2 −5𝑥−5ℎ −𝑥 2 +5𝑥
• 𝑓′ 𝑥 = lim
ℎ→0 ℎ

Kimaro_Novat_MU-MCC 110
 DIFFERENTIAL CALCULUS
2𝑥ℎ+ℎ2 −5ℎ
• 𝑓′ 𝑥 = lim
ℎ→0 ℎ
• 𝑓 ′ 𝑥 = lim (2𝑥 + ℎ − 5)
ℎ→0
• 𝑓 ′ 𝑥 = 2𝑥 − 5
• At (2, −6)
• 𝑓 ′ 2 = 2 2 − 5 = −1
• The slope is −1

Kimaro_Novat_MU-MCC 111
 DIFFERENTIAL CALCULUS
Differentiation from first principles.
• Suppose 𝑓 𝑥 is a continuous function, let 𝛿𝑥 be the increment in 𝑥
and 𝛿𝑦 be the increment in 𝑦 then 𝑦 = 𝑓 𝑥 becomes;
• 𝑦 + 𝛿𝑦 = 𝑓(𝑥 + 𝛿𝑥)
• 𝛿𝑦 = 𝑓 𝑥 + 𝛿𝑥 − 𝑓 𝑥
From the ratio then;
𝛿𝑦 𝑑𝑦 𝑓 𝑥+𝛿𝑥 − 𝑓(𝑥)
lim = = lim
𝛿𝑥→0 𝛿𝑥 𝑑𝑥 𝛿𝑥→0 𝛿𝑥
Which is the general rule called the first principles of differentiation.

Kimaro_Novat_MU-MCC 112
 DIFFERENTIAL CALCULUS
In other ways the formula can be written as
Δ𝑦 𝑑𝑦 𝑓 𝑥+∆𝑥 − 𝑓 𝑥
𝑓 ′ 𝑥 = lim = = lim
∆𝑥→0 Δ𝑥 𝑑𝑥 ∆𝑥→0 ∆𝑥

′ 𝑓 𝑥+ℎ − 𝑓 𝑥
or 𝑓 𝑥 = lim
ℎ→0 ℎ

Kimaro_Novat_MU-MCC 113
 DIFFERENTIAL CALCULUS
Use the general rule above find the derivative
of the following functions
2
1. 𝑓 𝑥 = 𝑥 + 4
2. 𝑦 = 5
3. 𝑦 = 3𝑥 − 5

Kimaro_Novat_MU-MCC 114
 DIFFERENTIAL CALCULUS
Solution to:
2
𝑓 𝑥 = 𝑥 + 4
2 2 2
𝑓 𝑥 + ℎ = 𝑥 + ℎ + 4 = 𝑥 + 2𝑥ℎ + ℎ +
4
′ 𝑓 𝑥+ℎ − 𝑓 𝑥
From 𝑓 𝑥 = lim
ℎ→0 ℎ

Kimaro_Novat_MU-MCC 115
 DIFFERENTIAL CALCULUS

′ 𝑥 2 +2𝑥ℎ+ℎ2 +4 − 𝑥 2 +4
𝑓 𝑥 = lim
ℎ→0 ℎ
2𝑥ℎ+ℎ2
𝑓 ′ 𝑥 = lim
ℎ→0 ℎ
′
𝑓 𝑥 = lim 2𝑥 + ℎ
ℎ→0
′
𝑓 𝑥 = 2𝑥 + 0 = 2𝑥

Kimaro_Novat_MU-MCC 116
 DIFFERENTIAL CALCULUS
Find the derivative from general rule.
1. 𝑦 = 3𝑥 − 5
2. 𝑓 𝑡 = 6𝑡 + 10
3. ℎ 𝑥 = 𝑥 − 6 (𝑥 + 2)
4. 𝑔 𝑥 = 𝑥(𝑥 − 1)
5. 𝑦 = 8𝑥
6. 𝑚 𝑥 = 45 − 3𝑥
Kimaro_Novat_MU-MCC 117
 DIFFERENTIAL CALCULUS
Derivative of Product of two Functions (Product Rule)
Let 𝑦 = 𝑓 × 𝑔 where all are functions of 𝑥 then
𝑦 ′ = 𝑓𝑔′ + 𝑔𝑓 ′
Proof: 𝑦 + ∆𝑦 = 𝑓 + ∆𝑓 × (𝑔 + ∆𝑔)
∆𝑦 = (𝑓𝑔 + 𝑓∆𝑔+∆𝑓𝑔 + ∆𝑓∆𝑔)−𝑓𝑔
∆𝑦 = 𝑓∆𝑔+∆𝑓𝑔 + ∆𝑓∆𝑔 dividing by ∆𝑥
∆𝑦= 𝑓∆𝑔+∆𝑓𝑔+∆𝑓∆𝑔

∆𝑥
Kimaro_Novat_MU-MCC 118
 DIFFERENTIAL CALCULUS
∆𝑦 𝑓∆𝑔+∆𝑓𝑔+∆𝑓∆𝑔
 = Introducing limits
∆𝑥 ∆𝑥
∆𝑦 𝑓∆𝑔+∆𝑓𝑔+∆𝑓∆𝑔 ∆𝑓∆𝑔
 lim = lim then =0
∆𝑥→0 ∆𝑥 ∆𝑥→0 ∆𝑥 ∆𝑥
Hence
𝑑 𝑓𝑔
 = 𝑦 ′ = 𝑓𝑔′ + 𝑔𝑓 ′
𝑑𝑥

Kimaro_Novat_MU-MCC 119
 DIFFERENTIAL CALCULUS
Derivative of Quotient of two Functions
𝑓 ′ 𝑓′ 𝑔−𝑓𝑔′ 𝑑𝑦
Let 𝑦 = then 𝑦 = =
𝑔 𝑔2 𝑑𝑥
𝑓
Proof:Let 𝑦 = then
𝑔
𝑓+∆𝑓
𝑦 + ∆𝑦 =
𝑔+∆𝑔

Kimaro_Novat_MU-MCC 120
 DIFFERENTIAL CALCULUS
𝑓+∆𝑓
• ∆𝑦 = −𝑦
𝑔+∆𝑔
𝑓+∆𝑓 𝑓
• ∆𝑦 = −
𝑔+∆𝑔 𝑔

𝑓+∆𝑓 𝑔−𝑓(𝑔+∆𝑔)
• ∆𝑦 =
𝑔(𝑔+∆𝑔)
𝑓𝑔+∆𝑓𝑔 −𝑓𝑔−𝑓∆𝑔)
• ∆𝑦 =
𝑔2 +𝑔∆𝑔)
Kimaro_Novat_MU-MCC 121
 DIFFERENTIAL CALCULUS
∆𝑓𝑔 −𝑓∆𝑔)
• ∆𝑦 =
𝑔2 +𝑔∆𝑔)
∆𝑓 ∆𝑔
∆𝑦 𝑔 −𝑓
• = ∆𝑥 ∆𝑥
∆𝑥 𝑔2 +𝑔∆𝑔
∆𝑦 𝑑𝑦 𝑔𝑓′ −𝑓𝑔′
• lim = = since 𝑔∆𝑔 → 0
∆𝑥→0 ∆𝑥 𝑑𝑥 𝑔2

Kimaro_Novat_MU-MCC 122
 DIFFERENTIAL CALCULUS
• Example1:Find the differential co-efficient
𝑓 𝑥 = 2𝑥 − 5 𝑥 3 + 3𝑥
Solution:
′ 2 3
• 𝑓 𝑥 = 2𝑥 − 5 3𝑥 + 3 + 𝑥 + 3𝑥 2
• 𝑓 ′ 𝑥 = 8𝑥 3 − 15𝑥 2 + 12𝑥 − 15

Kimaro_Novat_MU-MCC 123
 DIFFERENTIAL CALCULUS
Example 2: Find the differential co-efficient of the
following function
2
𝑥 −1
𝑦= 2
𝑥 +1

2 𝑑 𝑑
𝑥 +1 𝑥 2 −1 2
− 𝑥 −1 𝑥 2 +1
• 𝑦′ = 𝑑𝑥 𝑑𝑥
𝑥 2 +1 2
Kimaro_Novat_MU-MCC 124
 DIFFERENTIAL CALCULUS

′ 𝑥 2 +1 2𝑥− 𝑥 2 −1 2𝑥
•𝑦 =
𝑥 2 +1 2
′ 2𝑥 3 +2𝑥 − 2𝑥 3 −2𝑥 4𝑥
•𝑦 = =
𝑥 2 +1 2 𝑥 2 +1 2

Kimaro_Novat_MU-MCC 125
 DIFFERENTIAL CALCULUS
• Qns. Find the differential co-efficient of the
following functions
1. 𝑓 𝑥 = 3𝑥 2 − 5 𝑥 2 + 2
1−3𝑥 2
2. 𝑦 = 2+4𝑥 2
3. 𝑔 𝑥 = 5𝑥(𝑥 − 7)
3−4𝑥
4. 𝑦 = 𝑥
Kimaro_Novat_MU-MCC 126
 DIFFERENTIAL CALCULUS
𝑥9
5.𝑦 = 3
7𝑥− 𝑥
𝑥+5 2
6.𝑓 𝑥 = 𝑥 −1
𝑥−1
4
7.𝑔 𝑥 = 9𝑥 − 17 𝑥 + 8𝑥
6 2
8.𝑓 𝑡 = 𝑡 2𝑡 − 4𝑡 + 5

Kimaro_Novat_MU-MCC 127
 DIFFERENTIAL CALCULUS

Maxima and Minima determination.

• A function 𝑓(𝑥) is said to have attained its
maximum value at 𝑥 = 𝑥𝑎 if the function ceases
to increase and begins to decrease at 𝑥 = 𝑥𝑎 .
• A function 𝑓(𝑥) is said to have attained its
minimum value at 𝑥 = 𝑥𝑎 if the function ceases
to decrease and begins to increase at 𝑥 = 𝑥𝑎 .
Kimaro_Novat_MU-MCC 128
 DIFFERENTIAL CALCULUS

• The graph of 𝑦 = 𝑓 𝑥 y

Max

0 x

Min

Kimaro_Novat_MU-MCC 129
 DIFFERENTIAL CALCULUS
• By means of calculus there two ways of
determining and identifying the stationary
points.
1. First derivative test through examining the
𝒅𝒚
change of signs of
𝒅𝒙
𝒅𝟐 𝒚
2. Second derivative test
𝒅𝒙𝟐
Kimaro_Novat_MU-MCC 130
 DIFFERENTIAL CALCULUS
𝒅𝟐 𝒚
Second Derivative Test: 𝟐
𝒅𝒙
𝑑𝑦 𝑑2𝑦
a) For a maximum point; = 0 and 2 < 0 (𝑎𝑡 𝑥=𝑥1 )
𝑑𝑥 2 𝑑𝑥
𝑑𝑦 𝑑 𝑦
b) For minimum point; = 0 and 2 > 0 (𝑎𝑡 𝑥=𝑥1 )
𝑑𝑥 𝑑𝑥 𝟐
𝑑𝑦 𝒅 𝒚
c) For Inflexion point; = 0 and 𝟐 =0 (𝑎𝑡 𝑥=𝑥1 )
𝑑𝑥 𝒅𝒙

Kimaro_Novat_MU-MCC 131
 DIFFERENTIAL CALCULUS
Example: Investigate the stationary points from the
given functions by using second derivative test
1. 𝑦 = 𝑥 2 − 2𝑥
2. 𝑦 =2𝑥 3 + 3𝑥 2 − 36𝑥 + 10

Kimaro_Novat_MU-MCC 132
 DIFFERENTIAL CALCULUS
By second derivative test
2
1. 𝑦 = 𝑥 − 2𝑥
𝑑𝑦
• = 2𝑥 − 2
𝑑𝑥
𝑑𝑦
• At a stationary point =0
𝑑𝑥
• 2𝑥 − 2 = 0
• Solving for 𝑥 then 𝑥 = 1
Kimaro_Novat_MU-MCC 133
 DIFFERENTIAL CALCULUS
𝑑2 𝑦
• 2 =2
𝑑𝑥
𝑑2𝑦
• At 𝑥 = 1 , =2>0
𝑑𝑥 2
• Thus since the second derivative is positive then
the point 1 is the minimum point and minimum
value is −1

Kimaro_Novat_MU-MCC 134
 DIFFERENTIAL CALCULUS
• Example 2: Determine the maximum and minimum value
of
2 3 1 2
𝑦 = 𝑥 + 𝑥 − 6𝑥 + 8.
3 2
Solution:
2 3 1 2
•𝑦 = 𝑥 + 𝑥 − 6𝑥 + 8
3 2
𝑑𝑦 2
• = 2𝑥 + 𝑥 − 6
𝑑𝑥
𝑑𝑦
• At max or min value =0
𝑑𝑥
Kimaro_Novat_MU-MCC 135
 DIFFERENTIAL CALCULUS
2
• 2𝑥 + 𝑥 − 6 = 0
• Solving for 𝑥 then 𝑥 = 3 𝑜𝑟 − 4
• By second derivative test
𝑑2 𝑦
• 2 = 4𝑥 + 1
𝑑𝑥
𝑑2𝑦
• At 𝑥 = 3, then ; =13 which is positive
𝑑𝑥 2

Kimaro_Novat_MU-MCC 136
 DIFFERENTIAL CALCULUS
𝑑2𝑦
• At 𝑥 = −4 then; = −15 which is negative
𝑑𝑥 2
• The corresponding values of 𝑦 are:
2 3 1 2
• For 𝑥 = 3: 𝑦 = ( ×3 )+ ( × 3 ) − (6 × 3) +
3 2
8
• 𝑦 = 12.5

Kimaro_Novat_MU-MCC 137
 DIFFERENTIAL CALCULUS
• For 𝑥 = −4
2 1
• 𝑦 = × (−4) + × (−4)2 − 6 × −4 + 8 =
3
3 2
− 42.7+8+24+8≈ −2.7
• 𝑦 ≈ −2.7
• Therefore the point 3,12.5 is minimum and
−4, −2.7 is the maximum point.
• The minimum and maximum values are 12.5 and
-2.7 respectively.
Kimaro_Novat_MU-MCC 138
 DIFFERENTIAL CALCULUS
Example 3:
A company has examined its cost structure and
revenue structure and has determined that C the
total cost, R total revenue, and 𝑥 the number of
2
units produced are related as 𝐶 = 100 + 0.015𝑥 ,
At R= 3𝑥 , Find the production rate 𝑥 that will
maximize profits of the company. Find the profit
when 𝑥 = 120.
Kimaro_Novat_MU-MCC 139
 DIFFERENTIAL CALCULUS
Solution:
2
• Given; 𝐶 = 100 + 0.015𝑥 , R= 3𝑥
• Let 𝜋 be profit
•𝜋 = 𝑅 − 𝐶
2
• 𝜋 = 3𝑥 − 100 + 0.015𝑥
• 𝜋 = 3𝑥 −100−0.015𝑥 2
𝑑𝜋
• At maximum profit =0
𝑑𝑥
Kimaro_Novat_MU-MCC 140
 DIFFERENTIAL CALCULUS
𝑑𝜋
• = 3 − 0.03x =0
𝑑𝑥
• 0.03𝑥 = 3
• 𝑥 = 100
• The production which will maximize profit is
𝑥 = 100
• At 𝑥 = 120;
2
• 𝜋 = 3(120) −100−0.015 120 =44
Kimaro_Novat_MU-MCC 141
 DIFFERENTIAL CALCULUS
QUESTIONS:
1.Find the maximum and minimum values of the function.
a) 𝑦 = 𝑥 3 − 12𝑥 + 21
b) 𝑦 = 2𝑥 3 − 9𝑥 2 − 24𝑥 + 18
c) 𝑦 = 𝑥 3
d) 𝑦 = 𝑥 5 − 5𝑥 4 + 5𝑥 3 − 1
2. If the demand function of the monopoly is 3𝑞 = 98 − 4𝑝 and average
cost is 3𝑞 + 2 where q is output and p is the price, find maximum profit
of the monopolist.

Kimaro_Novat_MU-MCC 142
 DIFFERENTIAL CALCULUS
3. A certain firm noticed that higher sales of a particular item which it
produces are achieved by lowering the price charged. As a result the
total revenue from the sales at first rises as the number of units sold
increases, reaches the highest point and then falls off. This pattern of
total revenue is described by the relation 𝑦 = 50,000 − 𝑥 − 200 2
Where y is the total revenue and x the number of units sold.
a) Find, what number of units sold maximizes total revenue?
b) What is the amount of this maximum revenue?
c) What would be the total revenue of 400 units were sold?

Kimaro_Novat_MU-MCC 143
 DIFFERENTIAL CALCULUS
4. The demand curve of the product of a monopolist company is given
1
by 𝑃 = 30 − x where P is the price and 𝑥 is the demand for output.
2
1 2
Show that the total revenue curve is given by 30𝑥 − 𝑥 and find the
2
level of demand for output when the total revenue is maximum.
6. Suppose a manufacturer can sell 𝑥 items per week at a price 𝑃 =
20 − 0,001𝑥 Tshs each when it costs 𝑦 = 5𝑥 + 2000 Tshs to produce 𝑥
items. Determine the number of items he should produce per week for
maximum profit.

Kimaro_Novat_MU-MCC 144
 INTEGRAL CALCULUS

Integration
• The integral calculus is the reverse of differential
calculus (converse).
• If ∅ 𝑥 be any differentiable function of 𝑥 such
that
𝑑
∅ 𝑥 = 𝑓(𝑥)
𝑑𝑥

Kimaro_Novat_MU-MCC 145
 INTEGRAL CALCULUS

• Then ∅ 𝑥 is called an anti-derivative or

primitive or an indefinite integral or simply an
integral of 𝑓(𝑥).
• Symbolically this is written as ∅ 𝑥 = 𝑓 𝑥 𝑑𝑥
and
• Is read as ∅ 𝑥 is the integral of 𝑓(𝑥) w.r.t.𝑥

Kimaro_Novat_MU-MCC 146
 INTEGRAL CALCULUS

• The process of finding the integral of a given

function is called integration and the given
function is called the integrand.
• The symbol  is used for integral and 𝑑𝑥 is
integral w.r.t.𝑥

Kimaro_Novat_MU-MCC 147
 INTEGRAL CALCULUS

• There are two types of integrals

1. Indefinite (no limits 𝑖. 𝑒 𝑑𝑥)
2. definite (limited over intervals
𝑏
i.e. 𝑎 𝑓(𝑥)𝑑𝑥 = 𝐹 𝑏 − 𝐹(𝑎).

Kimaro_Novat_MU-MCC 148
 INTEGRAL CALCULUS

Rules of Integration
(a) The integral of a constant 𝑘𝑑𝑥 = 𝑘𝑥+c
(b) The integral of sum or difference of functions
is equal to the sum or difference of their integrals
i.e. 𝑓1 𝑥 + 𝑓2 𝑥 + ⋯ 𝑓𝑛 𝑑𝑥 = 𝑓1 𝑑𝑥 +
𝑓2 𝑑𝑥 + ⋯ + 𝑓𝑛 𝑑𝑥
Kimaro_Novat_MU-MCC 149
 INTEGRAL CALCULUS
(c) Integral of difference
𝑓1 𝑥 − 𝑓2 𝑥 𝑑𝑥 = 𝑓1 𝑥 𝑑𝑥 − 𝑓2 𝑥 𝑑𝑥

𝑥 𝑛+1
(d) Integral of power 𝑥 𝑛 𝑑𝑥 = +𝑐
𝑛+1

Kimaro_Novat_MU-MCC 150
 INTEGRAL CALCULUS
Note:
1
a) 𝑥
𝑑𝑥 = 𝑙𝑛𝑥 + 𝑐
𝑎𝑥 1 𝑎𝑥
b) 𝑒 𝑑𝑥 =
𝑎
𝑒 +𝑐

𝑎𝑥
a) 𝑎 𝑥 𝑑𝑥 = +𝑐
𝑙𝑛𝑎
• Integration by parts
𝑢𝑑𝑣 = 𝑢𝑣 − 𝑣𝑑𝑢

Kimaro_Novat_MU-MCC 151
 INTEGRAL CALCULUS
Examples: Evaluate the following integral
a) 3𝑑𝑥
• Solution: 3𝑑𝑥 = 3𝑥 + 𝑐
b) 6𝑥 3 + 7𝑥 2 + 2𝑥 − 8 𝑑𝑥
Solution:
3 2 3 4 7 3
6𝑥 + 7𝑥 + 2𝑥 − 8 𝑑𝑥 = 𝑥 + 𝑥 +𝑥 2 − 8𝑥 + 𝑐
2 3
Kimaro_Novat_MU-MCC 152
 INTEGRAL CALCULUS
2𝑥 2 𝑥 1
c) 𝑒 + + − 3 𝑑𝑥
𝑥 6 𝑥
2𝑥 2 𝑥 1
Solution: 𝑒 + + − 3 𝑑𝑥
𝑥𝑥 6
2𝑥
2 𝑥 1
= 𝑒 𝑑𝑥 + 𝑑𝑥 + 𝑑𝑥 − 3 𝑑𝑥
𝑥 6 𝑥
1
2𝑥 1 1 −
= 𝑒 𝑑𝑥+2 𝑑𝑥 + 𝑥𝑑𝑥- 𝑥 3
𝑥 6
Kimaro_Novat_MU-MCC 153
 INTEGRAL CALCULUS
1 2𝑥 1 2 3 2
= 𝑒 + 2ln 𝑥 + 𝑥 − 𝑥 3 +c
2 12 2
5
d) (5𝑥 + 7) 𝑑𝑥
5
Solution: (5𝑥 + 7) 𝑑𝑥 let 𝑢 = 5𝑥 + 7
𝑑𝑢 = 5𝑑𝑥 then
5 1
(5𝑥 + 7) 𝑑𝑥 = 𝑢5 𝑑𝑢
5
Kimaro_Novat_MU-MCC 154
 INTEGRAL CALCULUS
1 5 1 6
• 𝑢 𝑑𝑢 = 𝑢 +𝑐
5 30
• But 𝑢 = 5𝑥 + 7
5 1 6
• (5𝑥 + 7) 𝑑𝑥 = 5𝑥 + 7 +𝑐
30
8 1
e) 4 𝑥−3
𝑑𝑥

Kimaro_Novat_MU-MCC 155
 INTEGRAL CALCULUS
8 1
• 4 𝑥−3
𝑑𝑥
• Solution: Let 𝑥 − 3 = 𝑢 → 𝑑𝑥 = 𝑑𝑢
• At 𝑥 = 4 → 𝑢 = 1 &𝑥 = 8 → 𝑢 = 5
8 1 51
• 4 𝑑𝑥 = 1 𝑢
𝑑𝑢
𝑥−3
5
• = 𝑙𝑛 𝑢 1 = 𝑙𝑛 5 − 𝑙𝑛 1 = ln 5

Kimaro_Novat_MU-MCC 156
 INTEGRAL CALCULUS
• Questions: Evaluate the following integrals;
1 2
1. 𝑥− 𝑥+
5 𝑥
𝑑𝑥
2. 1 − 4𝑥 1 − 𝑥 𝑑𝑥
𝑥 3 +4
3. 𝑥 2 𝑑𝑥
2 3
𝑥 −3𝑥+ 𝑥+6
4. 𝑥
𝑑𝑥

Kimaro_Novat_MU-MCC 157
 INTEGRAL CALCULUS
2 3
5. 𝑥(𝑥 + 5) 𝑑𝑥
8𝑥 2
6. 3 𝑑𝑥
𝑥 3 +4 4
11
7. 3
2𝑥 + 5 𝑑𝑥

Kimaro_Novat_MU-MCC 158
 INTEGRAL CALCULUS
1
8. −1 2𝑥 2 − 𝑥 3 dx
4
9. 2 3𝑥 − 2 2 𝑑𝑥
−1 1 1
10. −3 2 − 3 𝑑𝑥
𝑥 𝑥
−𝑥
3
11. −2 𝑒 2 𝑑𝑥

Kimaro_Novat_MU-MCC 159
 INTEGRAL CALCULUS

Applications of Integration
Example: Find the total cost if marginal cost is
40
given by MC(𝑥) = where 𝑥 denotes output
𝑥
produced. Also find the total cost when 𝑥 =
0 𝑎𝑛𝑑 𝑥 = 100.
Solution:
Kimaro_Novat_MU-MCC 160
INTEGRAL CALCULUS
𝑑𝑇𝐶(𝑥)
𝑀𝐶(𝑥) =
𝑑𝑥

𝑑𝑇𝐶 𝑥 = 𝑀𝐶 𝑥 𝑑𝑥

𝑇𝐶 𝑥 = 𝑀𝐶 𝑥 𝑑𝑥

Kimaro_Novat_MU-MCC 161
 INTEGRAL CALCULUS
1
40 −
• 𝑇𝐶 𝑥 = 𝑑𝑥 = 40𝑥 2 𝑑𝑥
𝑥
1
− +1
𝑥 2
= 40 +𝑐
1
− +1
2

= 80 𝑥 + 𝑐
Kimaro_Novat_MU-MCC 162
 INTEGRAL CALCULUS

• At 𝑥 = 0
• 𝑇𝐶 0 = 80 0 + 𝑐 = 𝑐
• At 𝑥 = 100.
• 𝑇𝐶 100 = 80 100 + 𝑐 = 800 + 𝑐

Kimaro_Novat_MU-MCC 163
 INTEGRAL CALCULUS
• Qn 1.If the marginal revenue function of a firm
in the production of output is 𝑀𝑅 = 40 – 10𝑞2
where 𝑞 is the level of output and total revenue is
120 at 3 units of output, find the total revenue
function.
• Qn 2. Given the marginal revenue 𝑀𝑅 (𝑥) =
2
12 − 8𝑥 + 𝑥 . Determine revenue function
where, 𝑥 denotes number of units of output sold.
Kimaro_Novat_MU-MCC 164
 INTEGRAL CALCULUS
Qn3. A certain organization has the Marginal cost
of 3 𝑞 − 4 2 when the level of production is
𝑞 units. How much would the Total Cost increase
if production is increased from 6 to 10.
Qn 4. Find the function 𝑓(𝑥) whose tangent has
slope 3𝑥 2 + 1for each value of 𝑥 and whose graph
passes through the point (2,6).
Kimaro_Novat_MU-MCC 165
 INTEGRAL CALCULUS
Qn 5. The population P(t) of a bacterial colony 𝑡
hours after observation begins is found to be
changing at the rate.
𝑑𝑃 0.1𝑡 −0.03𝑡
= 200𝑒 + 150𝑒
𝑑𝑡
If the population was 200,000 bacteria when
observations began, what will the population be12
hours later?
Kimaro_Novat_MU-MCC 166
 INTEGRAL CALCULUS
Qn 6. The price p(dollars) of each unit of a particular
commodity is estimated to be changing at the rate
𝑑𝑝 −135𝑥
=
𝑑𝑥 9+𝑥 2
where 𝑥(hundred) units is the consumer demand (the
number of units purchased at that price).Suppose
400 units (𝑥 = 4) are demanded when the price is
$30 per unit.
Kimaro_Novat_MU-MCC 167
 INTEGRAL CALCULUS

Required:
a) Find the demand function 𝑝(𝑥).
b) At what price will 300 units be demanded? At
what price will no units be demanded?
c) How many units are demanded at a price of $20
per unit?

Kimaro_Novat_MU-MCC 168
PART B
STATISTICS

Kimaro_Novat_MU-MCC 169
 INTRODUCTION TO STATISTICS
• What is statistics?
• Statistics is a very broad subject, with
applications in a vast number of different fields.
• In general one can say that statistics is the
methodology for collecting, analyzing,
interpreting and drawing conclusions from
information.
Kimaro_Novat_MU-MCC 170
 INTRODUCTION TO STATISTICS
There are two major types of statistics.
1. Descriptive statistics
2. Inferential statistics

Kimaro_Novat_MU-MCC 171
 INTRODUCTION TO STATISTICS
• The branch of statistics devoted to the
summarization and description of data is called
descriptive statistics(includes the construction
of graphs, charts, and tables, and the calculation
of various descriptive measures such as averages,
measures of variation, and percentiles)

Kimaro_Novat_MU-MCC 172
 INTRODUCTION TO STATISTICS
• and the branch of statistics concerned with using
sample data to make an inference about a
population is called inferential statistics (
includes methods like point estimation, interval
estimation and hypothesis testing which are all
based on probability theory).

Kimaro_Novat_MU-MCC 173
 INTRODUCTION TO STATISTICS
• Population and Sample are two basic concepts
of statistics.
• Population is the collection of all individuals or
items under consideration in a statistical study.
• A Sample is that part of the population from
which information is collected.

Kimaro_Novat_MU-MCC 174
 INTRODUCTION TO STATISTICS
The uses and misuses of statistics

Kimaro_Novat_MU-MCC 175
 INTRODUCTION TO STATISTICS
• Misuse of statistics
• Misuse of statistics occurs when a statistical
argument asserts a falsehood.
• In some cases, the misuse may be accidental, In
others, it is purposeful and for the gain of the
perpetrator.

Kimaro_Novat_MU-MCC 176
 INTRODUCTION TO STATISTICS
• Types of misuse
1. Discarding unfavorable observations

Kimaro_Novat_MU-MCC 177
INTRODUCTION TO STATISTICS

Kimaro_Novat_MU-MCC 178
INTRODUCTION TO STATISTICS

Kimaro_Novat_MU-MCC 179
INTRODUCTION TO STATISTICS

Kimaro_Novat_MU-MCC 180
INTRODUCTION TO STATISTICS

Kimaro_Novat_MU-MCC 181
INTRODUCTION TO STATISTICS

Kimaro_Novat_MU-MCC 182
INTRODUCTION TO STATISTICS

Kimaro_Novat_MU-MCC 183
INTRODUCTION TO STATISTICS

Kimaro_Novat_MU-MCC 184
 INTRODUCTION TO STATISTICS
Sources of statistical data in Tanzania
• Question: What are the sources of statistical data
in Tanzania?

Kimaro_Novat_MU-MCC 185
 DATA COLLECTION METHODS
• Data collection is the process of gathering
and measuring information on targeted variables
in an established systematic fashion, which then
enables one to answer relevant questions and
evaluate outcomes.

Kimaro_Novat_MU-MCC 186
 DATA COLLECTION METHODS
• The choice of method is influenced by the data
collection strategy, the type of variable, the
accuracy required, the collection point and the
skill of the enumerator.
• There are two major types of data you can
collect, that can be further broken down into
subcategories.
Kimaro_Novat_MU-MCC 187
 DATA COLLECTION METHODS
1. Primary data
• Primary data, also known as raw data, is the data
you collect yourself and are the first person to
interpret.
• It’s data that’s gotten directly from the source.

Kimaro_Novat_MU-MCC 188
 DATA COLLECTION METHODS
2. Secondary data
• Secondary data refers to information you use
which has been collected, analyzed, and
structured by another person or group.
• Things like research papers, books, other
websites, etc. can be considered primary data
that, when used by you, are secondary data.
Kimaro_Novat_MU-MCC 189
 DATA COLLECTION METHODS
• The main data collection methods are but not
limited to:
• Direct observation, Interviewing, Questionnaires,
Extraction from Published records.

Kimaro_Novat_MU-MCC 190
 DATA COLLECTION METHODS
1. Direct observation (participant or non-
participant)
• Under the observation method, the information is
sought by way of investigator’s own direct
observation without asking from the respondent.

Kimaro_Novat_MU-MCC 191
 DATA COLLECTION METHODS
2. Interview
• Structured or unstructured one-on-one directed
conversations with key individuals or leaders in a
community.
• An interview can be conducted in person, over
the phone with a reliable cloud or via a video
call.
Kimaro_Novat_MU-MCC 192
 DATA COLLECTION METHODS
3. Extraction from Published records
• This data collection method is used when you
can’t take advantage of primary data.
• Instead, you’re able to use information that has
already been gathered from primary sources and
made available to the public.

Kimaro_Novat_MU-MCC 193
 DATA COLLECTION METHODS
• The advantage of published records is faster than
in-person interviews and you can use multiple data
sources together to get a more holistic picture.
• The disadvantage is that, reliant on the quality of
the third party for your data and it may be difficult
to find data that’s directly related to the problem
you want to solve.

Kimaro_Novat_MU-MCC 194
 DATA COLLECTION METHODS
4. Questionnaires.
• A questionnaire consists of a number of
questions printed or typed in a definite order on a
form or set of forms.
• In this method a questionnaire is sent (usually by
post) to the persons concerned with a request to
answer the questions and return the
questionnaire. Kimaro_Novat_MU-MCC 195
 DATA COLLECTION METHODS
Question: Explain the advantages and
disadvantages of each of the data collection
method.

Kimaro_Novat_MU-MCC 196
 PRESENTATION OF STATISTICAL DATA

• Presentation of data, this refers to the

organization of data into tables, graphs or charts,
so that logical and statistical conclusions can be
derived from the collected measurements.

Kimaro_Novat_MU-MCC 197
PRESENTATION OF STATISTICAL DATA

Common ways of data presentation

1. Text presentation
2. Semi – tabular presentation,
3. Tabular presentation
4. Graphic presentation(bar charts, histograms,
ogives, pie- charts, etc.)

Kimaro_Novat_MU-MCC 198
 PRESENTATION OF STATISTICAL DATA

1. Text presentation
• In this method, data are fundamentally presented
in paragraphs or sentences.
• Example of text presentation “The incidence rate
of a certain disease was 11% in 2016 and 15% in
2017; no significant difference of incidence rates
was found between the two years.”
Kimaro_Novat_MU-MCC 199
 PRESENTATION OF STATISTICAL DATA

2. Semi – tabular presentation

• Use both text and table

Kimaro_Novat_MU-MCC 200
 PRESENTATION OF STATISTICAL DATA

3. Tabular presentation
• A systematic organization of data in columns
and rows.
• Parts of the statistical table:
(a) Table heading
• Consists of table number and title

Kimaro_Novat_MU-MCC 201
PRESENTATION OF STATISTICAL DATA

(b) The Box Head (column captions)

• Caption refers to the headings of the columns.
• It consists of one or more column heads.
• A caption should be brief, concise and self-
explanatory, Column heading is written in the
middle of a column in small letters.

Kimaro_Novat_MU-MCC 202
PRESENTATION OF STATISTICAL DATA

(c) Stub ( Row captions) .

• Stub refers to the headings of rows.
• The horizontal headings and sub heading of the
row are called row captions and the space where
these rows headings are written is called stub.

Kimaro_Novat_MU-MCC 203
 PRESENTATION OF STATISTICAL DATA

(d) Body
• This is the most important part of a table.
• It contains a number of cells which are formed
due to the intersection of rows and columns.
• Data are entered in these cells.

Kimaro_Novat_MU-MCC 204
 PRESENTATION OF STATISTICAL DATA

(e) Foot Note

• A foot note is given at the bottom of a table.
• It helps in clarifying the point which is not clear
in the table.
(f) Source Note
• It shows the source of the data presented in the
table.
Kimaro_Novat_MU-MCC 205
PRESENTATION OF STATISTICAL DATA

Kimaro_Novat_MU-MCC 206
 PRESENTATION OF STATISTICAL DATA
• Questions : 1. Identify all parts of this table.

Kimaro_Novat_MU-MCC 207
 PART II: STATISTICS
2. The scores of BHRM1 in QMS100 was found to
be as follow in a test:

21 26 46 22 28 32 36 23

36 42 28 32 36 43 23 33

45 28 30 46 21 44 47 48

40 35 31 24 33 48 27 36
 PART II: STATISTICS
a) Prepare a frequency distribution table without
grouping data
b) Construct the frequency table by grouping
the data using the intervals 20-24, 25-29, …
c) Construct the cumulative frequency table.
 PRESENTATION OF STATISTICAL DATA

4. Graphic presentation
a) Bar charts
b) Histograms
c) Ogives
d) Pie- charts, etc.

Kimaro_Novat_MU-MCC 210
PRESENTATION OF STATISTICAL DATA

(a) Bar charts

• A bar graph is a way to visually represent qualitative data.
• Qualitative or categorical data occurs when the information
concerns a trait or attribute and is not numerical.
• This kind of graph emphasizes the relative sizes of each of
the categories being measured by using vertical or
horizontal bars.

Kimaro_Novat_MU-MCC 211
PRESENTATION OF STATISTICAL DATA

Each trait corresponds to a different bar.

There are various kinds of bar graph such as:
• Simple bar graph
• Grouped bar graph
• Compound bar graph

Kimaro_Novat_MU-MCC 212
PRESENTATION OF STATISTICAL DATA
• Use the data below to draw a simple bar graph

Kimaro_Novat_MU-MCC 213
 PRESENTATION OF STATISTICAL DATA

• Bar chart

Kimaro_Novat_MU-MCC 214
 PRESENTATION OF STATISTICAL DATA

Qns. Use the following information to draw a bar

graph.

Kimaro_Novat_MU-MCC 215
PRESENTATION OF STATISTICAL DATA

(b) Histograms
• In histogram rectangles are drawn so that the
area of each rectangle is proportional to the
frequency in the range of covered by it.
• The histogram is plotted as frequencies against
class marks which are the midpoints of the class
intervals.
Kimaro_Novat_MU-MCC 216
PRESENTATION OF STATISTICAL DATA

• Example: Draw histogram from the following

data

Kimaro_Novat_MU-MCC 217
PRESENTATION OF STATISTICAL DATA

Histogram
25

20
Frequency

15

10

0
12 17 22 27

Class Marks
Kimaro_Novat_MU-MCC 218
PRESENTATION OF STATISTICAL DATA

(c) The Cumulative Frequency Curve (OGIVE)

• This is drawn by taking upper boundaries (upper
real limits) against cumulative frequencies.
• Example;
• Construct an Ogive from the following data:

Kimaro_Novat_MU-MCC 219
PRESENTATION OF STATISTICAL DATA

Kimaro_Novat_MU-MCC 220
PRESENTATION OF STATISTICAL DATA

Cumulative Frequency Curve

35
Cumulative Frequency

30

25

20

15

10

0
2.5 5.5 8.5 11.5 14.5 17.5 20.5

Upper Boundaries
Kimaro_Novat_MU-MCC 221
PRESENTATION OF STATISTICAL DATA

• Question
• Consider the following frequency distribution which shows the
marks of 330 candidates in an examination then;
a) Construct cumulative frequency distribution
b) Draw histogram
c) Draw an Ogive
d) Draw Frequency Polygon

Kimaro_Novat_MU-MCC 222
PRESENTATION OF STATISTICAL DATA

Kimaro_Novat_MU-MCC 223
PRESENTATION OF STATISTICAL DATA

(d) Pie Chart(Circular graph)

• This is also called divided circle
• Steps in drawing a pie chart
1. Find sum of the given items
2. Compute for the degree for each item
3. Find also the percentage for each item
Kimaro_Novat_MU-MCC 224
PRESENTATION OF STATISTICAL DATA

• Example: The export of sisal of some countries

were represented in the table below.
• Draw a pie chart representing the data

Kimaro_Novat_MU-MCC 225
PRESENTATION OF STATISTICAL DATA

Kimaro_Novat_MU-MCC 226
PRESENTATION OF STATISTICAL DATA
EXPORT OF SISAL FROM SOME COUNTRIES

19.5
23.4
93.4

TANZANIA
RWANDA
KENYA
UGANDA
136.2 BURUNDI

87.6

Kimaro_Novat_MU-MCC 227
Measures of Central Tendency

• Introduction
• A measure of central tendency (or statistical
averages) is a single value that attempts to
describe a set of data by identifying the central
position within that set of data.

Kimaro_Novat_MU-MCC 228
Measures of Central Tendency
• The common measures of central tendency are
mean, median and the mode.
• The mean, median and mode are all valid
measures of central tendency, but under different
conditions, some measures of central tendency
become more appropriate to use than others

Kimaro_Novat_MU-MCC 229
Measures of Central Tendency
1. Mean Arithmetic
• The mean (or average) is the most popular and
well known measure of central tendency.
• It can be used with both discrete and continuous
data, although its use is most often with
continuous data.

Kimaro_Novat_MU-MCC 230
Measures of Central Tendency
• The mean is equal to the sum of all the values in
the data set divided by the number of values in
the data set (Ungrouped data).
• Let the values be 𝑥1 , 𝑥2 , 𝑥3 , … , 𝑥𝑛 then
𝑛 𝑥1 +𝑥2 +𝑥3 +,…+𝑥𝑛
•𝑥= 𝑖=1 𝑥𝑖 =
𝑛
• The Arithmetic mean is denoted as 𝑥
Kimaro_Novat_MU-MCC 231
Measures of Central Tendency
• For the frequency distribution the Arithmetic
mean is computed as
• Let the values be 𝑥1 , 𝑥2 , 𝑥3 , … , 𝑥𝑛 and
𝑓1 , 𝑓2 , 𝑓3 … , 𝑓𝑛 be their corresponding
frequencies then;
𝑛
𝑥1 𝑓1 +𝑥2 𝑓2 +𝑥3 𝑓3 +,…+𝑥𝑛 𝑓𝑛 𝑖 𝑥 𝑖 𝑓𝑖
•𝑥 = = 𝑛𝑓
𝑓1 +𝑓2 +𝑓3 +⋯+𝑓𝑛 𝑖 𝑖

Kimaro_Novat_MU-MCC 232
Measures of Central Tendency
• Examples.
1. Find the mean of the set of data
30, 45, 78, 65, 56,73,66
• Let 𝑥𝑖 be the values and n be the total number of
values then;
𝑛=7

𝑥𝑖 = 30 + 45 + 78 + 65 + 56 + 73 + 66 = 413
𝑖=1
Kimaro_Novat_MU-MCC 233
Measures of Central Tendency
413
•𝑥 = = 59
7
2. Find the mean from the following frequency
distribution.

Kimaro_Novat_MU-MCC 234
Measures of Central Tendency
𝑛
𝑖 𝑥 𝑖 𝑓𝑖
• Solution: Mean= 𝑛𝑓
𝑖 𝑖

Kimaro_Novat_MU-MCC 235
Measures of Central Tendency
370
• Mean= = 4.6835443
79
3. The following distribution shows the heights of
students in centimeters. Find the mean height of
the distribution.

Kimaro_Novat_MU-MCC 236
Measures of Central Tendency
• Let 𝑓 number of students, 𝑥 be class Marks.

Kimaro_Novat_MU-MCC 237
Measures of Central Tendency
• Mean heights
7325
=
50
= 146.5cm

Kimaro_Novat_MU-MCC 238
Measures of Central Tendency
2. The Mode
• The mode is the most frequent score/value in the
data set.
• The mode has the advantage that it eliminates the
effect of extreme values and easy to calculate.
• The mode can be unimodal, bimodal,…

Kimaro_Novat_MU-MCC 239
Measures of Central Tendency
• Examples. Determine the mode from the
following distributions.
a) For raw data (ungroup data).
i. 4, 6, 6, 5, 10, 3, 4, 6, 7, 8
ii. 1, 8, 17, 1, 13, 4, 5, 6,9
iii. 3, 3, 2, 5, 3, 8,6,6,6
Kimaro_Novat_MU-MCC 240
Measures of Central Tendency
• Solution:
i. 4, 6, 6, 5, 10, 3, 4, 6, 7, 8 ;Mode is 6
ii. 1, 8, 17, 1, 13, 4, 5, 6,9; Mode is 1
iii. 3, 3, 2, 5, 3, 8, 6, 6, 6; Mode is 3 & 6

Kimaro_Novat_MU-MCC 241
Measures of Central Tendency
b) Grouped Data
• For the frequency distribution the mode can be
estimated from the histogram or computed by the
formula.
𝑡1
• 𝑀𝑜𝑑𝑒 = 𝐿 + 𝑖, Where;
𝑡1 +𝑡2

Kimaro_Novat_MU-MCC 242
Measures of Central Tendency
• 𝐿 the lower limit of the modal class is.
• 𝑡1 is the difference between the frequency of the
modal class and that before the modal class
• 𝑡2 is the difference between the frequency of the
modal class and that after the modal class and
• 𝑖 is the class size (class width)

Kimaro_Novat_MU-MCC 243
Measures of Central Tendency
• Example: The following distribution shows the
heights of students in centimeters. Find the
modal height of the distribution.

Kimaro_Novat_MU-MCC 244
Measures of Central Tendency
• Solution: the modal class is 145-154
• 𝐿 = 145 − 0.5 = 144.5
• 𝑡1 = 12 − 11 = 1
• 𝑡2 = 12 − 10 = 2
• 𝑖 = 154.5 − 144.5 = 10
1
• 𝑀𝑜𝑑𝑒 = 144.5 + × 10 = 147.833333
1+2
Kimaro_Novat_MU-MCC 245
Measures of Central Tendency
3. The Median
• The median is the middle score for a set of data that has
been arranged in order of magnitude.
• The median is less affected by outliers and skewed data.
• If the total number of observation is odd, the median will
𝑵+𝟏 𝒕𝒉
be the value in the ordered set of scores, where N
𝟐
is the total number of observation.

Kimaro_Novat_MU-MCC 246
Measures of Central Tendency
• If the total number of observation is even, then
𝑵 𝒕𝒉 𝑵 𝒕𝒉
+ +𝟏
𝟐 𝟐
the median will be value.
𝟐
• The median for grouped data (frequency
distribution) can be estimated from the
cumulative frequency curve or can be computed
by the formula;
Kimaro_Novat_MU-MCC 247
Measures of Central Tendency
𝑁
− 𝑓𝑏
• 𝑀𝑒𝑑𝑖𝑎𝑛 = 𝐿 + 2
𝑖 Where;
𝑓𝑤

• L is the lower class boundary of the median class

• N is the total number of observation
• 𝑓𝑏 is the sum of frequencies before the median class
• 𝑓w is the frequency within the median class.
• 𝑖 is the class size.
Kimaro_Novat_MU-MCC 248
Measures of Central Tendency
• Examples
• Find the median of the following distributions
1. 8, 8, 2, 3, 4, 2, 8, 9, 32
2. 37, 40,26, 31,29,38, 39,42
• Solution:
1. 8, 8, 2, 3, 4, 2, 8, 9, 32
Kimaro_Novat_MU-MCC 249
Measures of Central Tendency
• Number of observation N= 9 − odd
• Arranging the values in ascending order
1. 2, 2, 3, 4, 8, 8, 8, 9, 32
𝟗+𝟏 𝒕𝒉 𝑡ℎ
Median= = 5 value;
𝟐
Median= 8

Kimaro_Novat_MU-MCC 250
Measures of Central Tendency
2. 37, 40,26, 31,29,38, 39,42
• Number of observation N= 8 − even
• 26, 29, 31, 37, 38, 39, 40, 42.
𝑵 𝒕𝒉 𝑵 𝒕𝒉
+ +𝟏
• Median= 𝟐 𝟐
value
𝟐
𝟖 𝒕𝒉 𝟖 𝒕𝒉
+ +𝟏 4 𝑡ℎ +5𝑡ℎ 37+38
• 𝑴𝒆𝒅𝒊𝒂𝒏 = 𝟐 𝟐
value= =
𝟐 2 2
Kimaro_Novat_MU-MCC 251
Measures of Central Tendency
• 𝑴𝒆𝒅𝒊𝒂𝒏 = 𝟑𝟕. 𝟓
• Compute median from the following frequency
distributions

Kimaro_Novat_MU-MCC 252
Measures of Central Tendency
• Solution.
• 𝑓 = 𝑁 = 50
𝑁 𝑡ℎ
• Median position= value
2
50 𝑡ℎ 𝑡ℎ
• Median position= value= 25 value
2

Kimaro_Novat_MU-MCC 253
Measures of Central Tendency
• Median class; 145-154
• 𝐿 = 144.5, 𝑓𝑏 = 22, 𝑓𝑤 = 12, 𝑖 = 10
𝑁
− 𝑓𝑏
• 𝑀𝑒𝑑𝑖𝑎𝑛 = 𝐿 + 2
𝑖
𝑓𝑤
50
−22
• 𝑀𝑒𝑑𝑖𝑎𝑛 = 144.5 + 2
10= 147
12

Kimaro_Novat_MU-MCC 254
Measures of Central Tendency
• Example; Find the median from the distributions.

Kimaro_Novat_MU-MCC 255
Measures of Central Tendency
• 𝑓 = 𝑁 = 100
100 𝑡ℎ
• Median position= value= 50𝑡ℎ value
2
• Median class; 𝟑𝟎 − 𝟒𝟎
• 𝐿 = 30, 𝑓𝑏 = 38, 𝑓𝑤 = 40, 𝑖 = 10
100
−38
• 𝑀𝑒𝑑𝑖𝑎𝑛 = 30 + 2
10= 33
40
Kimaro_Novat_MU-MCC 256
Measures of Central Tendency
• QUESTIONS FOR REVISION.
1. Compute the mean, mode and median from the
following frequency distribution.

Kimaro_Novat_MU-MCC 257
Measures of Central Tendency
2. The distribution of marks obtained by 199
students in a mathematics examination is shown in
a table;

• Calculate :Median, mode and mean marks.

Kimaro_Novat_MU-MCC 258
Measures of Central Tendency
3. The length of life ( to nearest hour) of each of
50 electric light bulbs is noted and the results
shown in the table below. Calculate for 𝑥 ,then
median, modal and mean length of life.

Kimaro_Novat_MU-MCC 259
Measures of Central Tendency
4. Find the mean, median and mode of the
following numbers:
2, 3, 3, 9, 6, 6, 12, 11, 8, 2, 3, 5, 7, 5, 4, 4, 5, 12, 9
5. Estimate the mean and median diameter of rods
produced by a particular machine given in the
table:

Kimaro_Novat_MU-MCC 260
Measures of Central Tendency
6. If the mean of the following numbers is 17, find
the value of 𝑡:
12, 18, 21, 𝑡, 13
7. The mean of 𝒏 numbers is 5. If the number 13
is now included with the 𝒏 numbers, the new
mean is 6. Find the value of 𝑛.

Kimaro_Novat_MU-MCC 261
Measures of Central Tendency
Geometric Mean
In mathematics, the geometric mean is a type
of mean or average, which indicates the central
tendency or typical value of a set of numbers by
using the product of their values.

Kimaro_Novat_MU-MCC 262
Measures of Central Tendency
• The geometric mean is defined as the nth root of
the product of n numbers.
• Consider the set of numbers:
• 𝑥1 , 𝑥2 , 𝑥3 , … … . , 𝑥𝑛 then
• G.M= 𝑛 𝑥1 × 𝑥2 × 𝑥3 , … … . ,× 𝑥𝑛

Kimaro_Novat_MU-MCC 263
Measures of Central Tendency
• Example:
• 1. What is the Geometric Mean of 10, 51.2 and
8?
• Solution.
• Geometric Mean = 3√(10 × 51.2 × 8) = 16

Kimaro_Novat_MU-MCC 264
Measures of Central Tendency
2. If Geometric mean(8,a)=12, what is a?
Solution: 8 × 𝑎 = 12
Squaring 8 × 𝑎 = 144
𝑎 =18

Kimaro_Novat_MU-MCC 265
Measures of Central Tendency
• Geometric Mean for Grouped Data
• Let the values be 𝑥1 , 𝑥2 , 𝑥3 , … , 𝑥𝑛 and
𝑓1 , 𝑓2 , 𝑓3 … , 𝑓𝑛 be their corresponding
frequencies then;
𝑛
• G.M= 𝑥1 𝑓1 𝑥2 𝑓2 𝑥3 𝑓3 … 𝑥𝑛 𝑓𝑛
• For 𝑛 = 𝑓

Kimaro_Novat_MU-MCC 266
Measures of Central Tendency
• Find the geometric mean of the distribution

9
• Solution:G.M= 302 × 401 × 152 × 502 × 602
= 35.40796562262

Kimaro_Novat_MU-MCC 267
Measures of Central Tendency
• Questions: Compute the geometric mean for
1. 30,40.8, 68,78.
2. Frequency Distributions

Kimaro_Novat_MU-MCC 268
Measures of Central Tendency
Harmonic Mean
• To find the harmonic mean of a set of n numbers,
add the reciprocals of the numbers in the set,
divide the sum by n, then take the reciprocal of
the result.
• The harmonic mean of {x1, x2, x3, x4, . . ., xn} is
given below
Kimaro_Novat_MU-MCC 269
Measures of Central Tendency
𝑛 𝑛
• Harmonic Mean(H)= 𝑛 1 = 1 1 1 1
𝑖=1𝑥 + + +⋯
𝑖 𝑥1 𝑥 2 𝑥3 𝑥𝑛
1 1 𝑛 1
• Or = ( 𝑖=1 ) ; where H is harmonic mean
𝐻 𝑛 𝑥𝑖
• Example: Calculate the Harmonic mean from the
data; 20, 14, 35, 18, 21

Kimaro_Novat_MU-MCC 270
Measures of Central Tendency
• Solution:20, 14, 35, 18, 21
𝑛 𝑛
H= 𝑛 1 = 1 1 1 1
𝑖=1𝑥 + + +⋯
𝑖 𝑥1 𝑥2 𝑥3 𝑥𝑛
5
H= 1 1 1 1 1 =19.74921630094
+ + + +
20 14 35 18 21

Kimaro_Novat_MU-MCC 271
Measures of Central Tendency
• Questions:
1. Find the Harmonic Mean of 1, 2, 3, 4, 5
2. Find harmonic mean of 13, 23, 12, 44, 55
3. Find harmonic mean of 5.5, 6.5, 10.8, 20.2
4. Find the harmonic mean of 30, 45, 52

Kimaro_Novat_MU-MCC 272
Measures of Central Tendency

Harmonic Mean for frequency distribution is

calculated by;
𝑓
H.M= 𝑓 where;
𝑥
f is the frequency corresponding to each
observation
Kimaro_Novat_MU-MCC 273
Measures of Central Tendency
Example: The following is the frequency
distribution of the marks(out of 40) obtained by
the students of a certain college in QMS.
Calculate harmonic mean.

Kimaro_Novat_MU-MCC 274
Measures of Central Tendency
• solution

Kimaro_Novat_MU-MCC 275
Measures of Central Tendency
260
• H.M= ≈ 24.33
10.68534
Question: Find H.M

Kimaro_Novat_MU-MCC 276
Measures of Central Tendency

Kimaro_Novat_MU-MCC 277
MEASURES OF DISPERSION

• Introduction
• While knowing the mean value for a set of data
may give us some information about the set
itself, many varying sets can have the same mean
value.

Kimaro_Novat_MU-MCC 278
MEASURES OF DISPERSION

• To determine how the sets are different, we need

more information.
• Another way of examining single variable data is
to look at how the data is spread out, or dispersed
about the mean.

Kimaro_Novat_MU-MCC 279
MEASURES OF DISPERSION

• The measures of dispersion of distribution are:

Range
Quartile deviation
Mean Deviation
Variance
Standard Deviation
Coefficient of Variation
Kimaro_Novat_MU-MCC 280
MEASURES OF DISPERSION

RANGE
• The simplest of our methods for measuring dispersion
is range.
• Range is the difference between the largest value and
the smallest value in the data set.
• While being simple to compute, the range is often
unreliable as a measure of dispersion since it is based
on only two values in the set.
Kimaro_Novat_MU-MCC 281
MEASURES OF DISPERSION

• Range=Highest Value−Lowest Value.

• Example. Find the range of the following
distributions 34, 36, 18, 78, 68, 10, 50.
• Solution: Highest value= 78, Lowest value= 10
• Range=Highest Value−Lowest Value.
• Range=78−10 = 68

Kimaro_Novat_MU-MCC 282
MEASURES OF DISPERSION

Quartile deviation
• Quartile deviation is a statistic that measures the
deviation in the middle of the data.
• Quartile deviation is also referred to as the semi
interquartile range and is half of the difference
between the third quartile and the first quartile
value
Kimaro_Novat_MU-MCC 283
MEASURES OF DISPERSION
• The formula

Kimaro_Novat_MU-MCC 284
MEASURES OF DISPERSION

• The quartile deviation is calculated differently

for ungrouped data and for the grouped data.
• Arrange the available data in ascending order for
both the grouped and ungrouped data.

Kimaro_Novat_MU-MCC 285
MEASURES OF DISPERSION

• For the case of ungrouped data:

(𝑛+1)
• 𝑄1 =
4
3(𝑛+1)
• 𝑄2 =
4
• Here n is for the particular quartile.

Kimaro_Novat_MU-MCC 286
MEASURES OF DISPERSION
• For the case of grouped data:
𝑁
− 𝑓𝑏
• 𝑄1 = 𝐿 + 4
𝑖
𝑓𝑤
3𝑁
− 𝑓𝑏
• 𝑄3 = 𝐿 + 4
𝑖
𝑓𝑤

Kimaro_Novat_MU-MCC 287
MEASURES OF DISPERSION

• Example 1: Find the quartile deviation for the

following given data.
• 23, 8, 5, 16, 33, 7, 24, 5, 30, 33, 37, 30, 9, 11,
26, 32

Kimaro_Novat_MU-MCC 288
MEASURES OF DISPERSION

• Solution:
• The given data points are 23, 8, 5, 16, 33, 7, 24,
5, 30, 33, 37, 30, 9, 11, 26, 32
• Let us arrange this data in the following
ascending order.
• 5, 5, 7, 8, 9, 11, 16, 23, 24, 26, 30, 30, 32, 33, 33,
37
Kimaro_Novat_MU-MCC 289
MEASURES OF DISPERSION

• From the above data we have

𝑄1 = ( 8 + 9)/2 = 17/2 = 8.5
𝑄3 = (30 + 32)/2 = 62/2 = 31
𝑄3−𝑄1 31−8.5
Q.D= = = 22.52
2 2
= 11.25

Kimaro_Novat_MU-MCC 290
MEASURES OF DISPERSION

• Example 2: Find the quartile deviation of the

marks scored by 50 students of a class.

Class Interval 45 - 50 50-55 55-60 60-65 65-70 70-75

of marks
Number of 7 5 12 11 9 6
Students
(Frequency)

Kimaro_Novat_MU-MCC 291
MEASURES OF DISPERSION

Kimaro_Novat_MU-MCC 292
MEASURES OF DISPERSION

• 𝑁 = 50
• 𝑁/4 = 50/4 = 12.5
• 3𝑁/4 = 3(50/4) = 2(12.5) = 37.5
• Hence the class containing 𝑄1 is 55 − 60, and
the class containing 𝑄3 is 65 − 70.
•𝑖 = 5

Kimaro_Novat_MU-MCC 293
MEASURES OF DISPERSION
𝑁
− 𝑓𝑏
• 𝑄1 = 𝐿 + 4
𝑖
𝑓𝑤
12.5−12
• 𝑄1 = 55 + 5 = 55.208
12

3𝑁
− 𝑓𝑏
• 𝑄3 = 𝐿 + 4
𝑖
𝑓𝑤
37.5−35
• 𝑄3 = 65 + 5 = 65.389
9

Kimaro_Novat_MU-MCC 294
MEASURES OF DISPERSION
𝑄3−𝑄1
• Q.D=
2
66.389−55.208
=
2
= 5.5905
• Therefore, the quartile deviation of the marks of
the students is 5.5905

Kimaro_Novat_MU-MCC 295
MEASURES OF DISPERSION

Mean Absolute Deviation( Mean Deviation)

• The mean absolute deviation is the mean of the
absolute value of the difference between the
individual value in the data set and the mean.
• The method tries to measure the average
distances between the values in the data set and
the mean.
Kimaro_Novat_MU-MCC 296
MEASURES OF DISPERSION

• For ungroup data, the mean deviation is

computed by the formula
𝑥 𝑖 −𝑥
• 𝑀𝐸𝐴𝑁 𝐷𝐸𝑉𝐼𝐴𝑇𝐼𝑂𝑁 = Where 𝑥 is the
𝑁
mean of the data set.
• Example: Compute the mean deviation from the
following distribution: 34, 36, 18, 78, 68, 10, 50.

Kimaro_Novat_MU-MCC 297
MEASURES OF DISPERSION

Solution:
34, 36, 18, 78, 68, 10, 50

34 + 36 + 18 + 78 + 68 + 10 + 50
𝑥=
7

= 42
Kimaro_Novat_MU-MCC 298
MEASURES OF DISPERSION

Kimaro_Novat_MU-MCC 299
MEASURES OF DISPERSION

• 𝑀𝐸𝐴𝑁 𝐷𝐸𝑉𝐼𝐴𝑇𝐼𝑂𝑁
𝑥𝑖 − 𝑥
=
𝑁
=
8+ 6 + 24+ 36 + 26 + 32 + 8
7
= 20

Kimaro_Novat_MU-MCC 300
MEASURES OF DISPERSION

• For frequency distribution/ Grouped data

𝑓 𝑥𝑖 −𝑥
• 𝑀𝐸𝐴𝑁 𝐷𝐸𝑉𝐼𝐴𝑇𝐼𝑂𝑁 =
𝑁
• Example: The distributions of heights of students
in a certain class are given in the table. Compute
the mean deviation.

Kimaro_Novat_MU-MCC 301
MEASURES OF DISPERSION

Kimaro_Novat_MU-MCC 302
MEASURES OF DISPERSION

• Solution:
𝑓 𝑥𝑖 −𝑥
• 𝑀𝐸𝐴𝑁 𝐷𝐸𝑉𝐼𝐴𝑇𝐼𝑂𝑁 =
𝑁
7325
• Computing for 𝑥 =Mean heights= =
50
146.5cm

Kimaro_Novat_MU-MCC 303
MEASURES OF DISPERSION

Kimaro_Novat_MU-MCC 304
MEASURES OF DISPERSION

• 𝑓 𝑥 − 𝑥 = 608
• 𝑓 = 50
608
• 𝑀𝐸𝐴𝑁 𝐷𝐸𝑉𝐼𝐴𝑇𝐼𝑂𝑁 = = 12.6
50

Kimaro_Novat_MU-MCC 305
MEASURES OF DISPERSION

 The Standard Deviation

• The standard deviation describes dispersion
in terms of the amount or size by which
measurements deviate from their mean
value.
• It is denoted as 𝜎

Kimaro_Novat_MU-MCC 306
MEASURES OF DISPERSION

For Ungroup Data

𝑥𝑖 −𝑥 2
•𝜎 =
𝑛
For group data (Frequency distribution)
𝑓 𝑖 𝑥 𝑖 −𝑥 2
•𝜎 =
𝑛

Kimaro_Novat_MU-MCC 307
MEASURES OF DISPERSION

THE VARIANCE
• The square of the standard deviation is called
2
the variance denoted as 𝜎 .
• For ungrouped data
𝑥 𝑖 −𝑥 2 𝑥2
• 𝜎2 = = − 𝑥 2
𝑛 𝑛

Kimaro_Novat_MU-MCC 308
MEASURES OF DISPERSION
• For group data( Frequency Distribution)
𝑓𝑖 𝑥𝑖 −𝑥 2
• 𝜎2 =
𝑛
• Where
• 𝜎 2 =Variance
• 𝑥𝑖 =items or observation
• 𝑥 =the mean
• n=total number of items
• 𝑥 − 𝑥 2 =sum of all deviations square.
Kimaro_Novat_MU-MCC 309
MEASURES OF DISPERSION

• NOTE:
a) If the standard deviation is zero then no deviation
at all and all observations are equal to mean.
b) If the standard deviation is small, this means that
the observations are close to the mean and there is
small degree of dispersion.
c) If the standard deviation is large there is a high
degree of dispersion from the mean.
Kimaro_Novat_MU-MCC 310
MEASURES OF DISPERSION

• Examples
• Compute the standard deviation and variance
from the following
1. 34, 36, 18, 78, 68, 10, 50.
34+36+18+78+68+10+50
• Solution: 𝑥 =
7
294
•𝑥 = = 42
7

Kimaro_Novat_MU-MCC 311
MEASURES OF DISPERSION

Kimaro_Novat_MU-MCC 312
MEASURES OF DISPERSION

𝑥𝑖 −𝑥 2 3736
•𝜎 = = = 23.1
𝑛 7
• Standard deviation is
2 𝑥 𝑖 −𝑥 2 3736
•𝜎 = = =533.6
𝑛 7
• Variance is

Kimaro_Novat_MU-MCC 313
MEASURES OF DISPERSION
2. The distributions of heights of students in a
certain class are given in the table.

Kimaro_Novat_MU-MCC 314
MEASURES OF DISPERSION

Kimaro_Novat_MU-MCC 315
MEASURES OF DISPERSION

2 𝑓 𝑖 𝑥 𝑖 −𝑥 2 10450
•𝜎 = =
𝑛 50
𝑓 𝑖 𝑥 𝑖 −𝑥 2
•𝜎 = =
𝑛
10450
•=
50

Kimaro_Novat_MU-MCC 316
MEASURES OF DISPERSION
Coefficient of Variation - CV'
• The coefficient of variation represents the ratio
of the standard deviation to the mean, and it is a
useful statistic for comparing the degree of
variation from one data series to another, even if
the means are drastically different from each
other.
Kimaro_Novat_MU-MCC 317
MEASURES OF DISPERSION
𝑺𝑻𝑨𝑵𝑫𝑨𝑹𝑫 𝑫𝑬𝑽𝑰𝑨𝑻𝑰𝑶𝑵
•𝐂 𝑽 =
𝑴𝑬𝑨𝑵
𝜎
• 𝐶𝑉 =
𝜇
• The series having greater coefficient of variation
is said to be more variable than the other and the
series having lower coefficient of variation is
said to be more consistent than the other.
Kimaro_Novat_MU-MCC 318
MEASURES OF DISPERSION
• Example. An analysis of monthly wages paid to
the workers in two firms A and B belonging to
the same industry give the following results.

Kimaro_Novat_MU-MCC 319
MEASURES OF DISPERSION
• Calculate the variability of individual wages.
• Solution.
• Variance of distribution of wages in firm A=$81
• Average monthly wages of firm A=$186
𝜎 81
• 𝐶𝑉 = = = 0.0484
𝜇 186

Kimaro_Novat_MU-MCC 320
MEASURES OF DISPERSION
• Variance of distribution of wages in firm B=$100
• Average monthly wages of firm B=$175
𝜎 100
• 𝐶𝑉 = = = 0.0571
𝜇 175
• Since, the CV of wages for firm B is greater than
coefficient of variation for firm A, then firm B
has greater variability in individual wages.
Kimaro_Novat_MU-MCC 321
MEASURES OF DISPERSION
Questions for Revision.
1. From the data given below, state which group
is more variable:

Kimaro_Novat_MU-MCC 322
MEASURES OF DISPERSION
2. We have two investment proposals, explain
which venture is riche.

Kimaro_Novat_MU-MCC 323
MEASURES OF DISPERSION
3. The scores of two students A and B in various
subjects each are:

• Which may be regarded as more consistent

student?

Kimaro_Novat_MU-MCC 324
MEASURES OF DISPERSION
4. The mean of the numbers 3, 6, 7, 𝑎, 14 is 8. Find
the standard deviation of the set of numbers.
5. For a set of 10 numbers 𝑥 = 290 and
𝑥 2 = 8469.Find the mean and the variance.
6. Find the mean and standard deviation of the
𝑛 1
first n integers.( Hint: use 𝑟=1 𝑟 = 𝑛 𝑛 + 1
1 2
𝑛 2
and 𝑟=1 𝑟 = 𝑛 𝑛 + 1 2𝑛 + 1
6
Kimaro_Novat_MU-MCC 325
MEASURES OF DISPERSION
7. In a certain village 400 inhabitants the
distribution of ages is as follows:

• Use the data to estimate the mean age and the

standard deviation, in years, each correct to 1
d.p.
Kimaro_Novat_MU-MCC 326
MEASURES OF DISPERSION
8. Bassart Electronics is considering employing one of
two training programs. Two groups were trained for
the same task. Group 1 was trained by program A,
group 2 by program B. For the fist group, the times
required to train the employees had an average of
32.11 hours and a variance of 68.09. In the second
group, the average was 19.75 hours and the variance
was 71.14. Which training program has less relative
variability in its performance?
Kimaro_Novat_MU-MCC 327
REGRESSION AND CORRELATION ANALYSIS

• Introduction
• So far we have dealt with those statistical
measures that we use in context of univariate
population i.e., the population consisting of
measurement of only one variable.

Kimaro_Novat_MU-MCC 328
REGRESSION AND CORRELATION ANALYSIS

• But if we have the data on two variables, we are

said to have a bivariate population and if the data
happen to be on more than two variables, the
population is known as multivariate
population.
• Thus we have to answer two types of questions
in bivariate or multivariate populations viz.,
Kimaro_Novat_MU-MCC 329
REGRESSION AND CORRELATION ANALYSIS

1. Does there exist association or correlation

between the two (or more) variables? If yes,
of what degree?
2. Is there any cause and effect relationship
between the two variables in case of the
bivariate population or between one variable
on one side and two or more variables on the
other side in case of multivariate population?
Kimaro_Novat_MU-MCC 330
REGRESSION AND CORRELATION ANALYSIS

2. cont.. If yes, of what degree and in which

direction?
• The first question is answered by the use of
correlation technique and the second question
by the technique of regression.

Kimaro_Novat_MU-MCC 331
REGRESSION AND CORRELATION ANALYSIS

 Scatter Diagram
• A graphical representation of bivariate data as set of
points in a plane that have Cartesian coordinates
equal to corresponding values of two variate.
• In other words a scatter diagram is a tool for
analyzing relationships between two variables.
• One variable is plotted on the horizontal axis and the
other is plotted on the vertical axis.
Kimaro_Novat_MU-MCC 332
REGRESSION AND CORRELATION ANALYSIS

• Consider the following relationships.

Kimaro_Novat_MU-MCC 333
REGRESSION AND CORRELATION ANALYSIS

• Consider the set of points

𝑋1 , 𝑌1 , 𝑋2 , 𝑌2 , 𝑋3 , 𝑌3 , … 𝑋𝑛 , 𝑌𝑛 .
• If the values of Y are plotted against the values X,
then a scatter diagram is obtained.
• Scatter diagrams will generally show one of six
possible correlations between the variables:

Kimaro_Novat_MU-MCC 334
REGRESSION AND CORRELATION ANALYSIS

1. Strong Positive Correlation, the value of Y

clearly increases as the value of X increases.
2. Strong Negative Correlation, the value of Y
clearly decreases as the value of X increases.
3. Weak Positive Correlation, the value of Y
increases slightly as the value of X increases.

Kimaro_Novat_MU-MCC 335
REGRESSION AND CORRELATION ANALYSIS

1. Weak Negative Correlation, the value of Y

decreases slightly as the value of X increases.
2. Complex Correlation, the value of Y seems to
be related to the value of X, but the
relationship is not easily determined.
3. No Correlation, there is no demonstrated
connection between the two variables.
Kimaro_Novat_MU-MCC 336
REGRESSION AND CORRELATION ANALYSIS

• Examples of scatter diagrams

Kimaro_Novat_MU-MCC 337
REGRESSION AND CORRELATION ANALYSIS

Kimaro_Novat_MU-MCC 338
REGRESSION AND CORRELATION ANALYSIS

Kimaro_Novat_MU-MCC 339
REGRESSION AND CORRELATION ANALYSIS

Example. The following data gives the test results

of 10 students. Draw a scatter diagram

Kimaro_Novat_MU-MCC 340
REGRESSION AND CORRELATION ANALYSIS

Kimaro_Novat_MU-MCC 341
REGRESSION AND CORRELATION ANALYSIS

Correlation Analysis
• Correlation is a measure of the degree of
association between two variables.
• For example, consider the variables family
income and family expenditure.
• It is well known that income and expenditure
increase or decrease together.
Kimaro_Novat_MU-MCC 342
REGRESSION AND CORRELATION ANALYSIS

• Thus they are related in the sense that change in

any one variable is accompanied by change in the
other variable.
• Again price and demand of a commodity are
related variables; when price increases demand
will tend to decreases and vice versa.
• If the change in one variable is accompanied by
a change in the other, then the variables are said
to be correlated.
Kimaro_Novat_MU-MCC 343
REGRESSION AND CORRELATION ANALYSIS

• Correlation can be studied through;

a) Karl Pearson’s coefficient of correlation Or
Product Moment Correlation Coefficient (𝑟)
b) Charles Spearman’s coefficient of correlation
or Rank Correlation Coefficient(𝜌).

Kimaro_Novat_MU-MCC 344
REGRESSION AND CORRELATION ANALYSIS

a) Karl Pearson’s Coefficient of Correlation

• Karl Pearson’s coefficient of correlation is also
known as the product moment correlation
coefficient.
• The value of ‘r’ lies between ± 1 i.e
• (−1 ≤ 𝑟 ≤ 1)

Kimaro_Novat_MU-MCC 345
REGRESSION AND CORRELATION ANALYSIS

• Karl Pearson’s coefficient of correlation can be

worked out as:
𝑛( 𝑋𝑌)−( 𝑋)( 𝑌)
•𝑟 =
𝑛 𝑋2− 𝑋 2 𝑛 𝑌2− 𝑌 2

Kimaro_Novat_MU-MCC 346
REGRESSION AND CORRELATION ANALYSIS

• Interpretation of the value of r

• The value of ‘r’ lies in the interval −1 ≤ 𝑟 ≤ 1
• For 𝑟 > 0 indicates positive correlation between the
two variables (i.e., changes in both variables take
place in the statement direction).
• If 𝑟 < 0 indicates negative correlation i.e., changes
in the two variables taking place in the opposite
directions.
Kimaro_Novat_MU-MCC 347
REGRESSION AND CORRELATION ANALYSIS

• If 𝑟 = 0 indicates that there is no association

between the two variables.
• When r = (+) 1, it indicates perfect positive
correlation and
• When it is (–) 1, it indicates perfect negative
correlation.
• The value of ‘r’ nearer to +1 or –1 indicates high
degree of correlation between the two variables.
Kimaro_Novat_MU-MCC 348
REGRESSION AND CORRELATION ANALYSIS

The following data were collected on seven employees to examine the relationship between job
stress(X) and employee performance (Y). The employees were asked to rate the job stress using a
scale of 1= minimum stress to 20 maximum stress

Observation
1 2 3 4 5 6 7
Job stress 8 2 5 12 15 9 6
Employee performance (100%) 78 92 90 58 43 74 81

(a) Compute the terms    

X , Y , XY , Y 2
and  X 2

Determine the Pearson correlation, r.

Kimaro_Novat_MU-MCC 349
REGRESSION AND CORRELATION ANALYSIS

(c) Make interpretation on the relationship between job stress and

employee performance.
𝑿 𝒀 𝑿𝟐 𝒀𝟐 𝑿𝒀

8 78 64 6084 624

2 92 4 8464 184

5 90 25 8100 450

12 58 144 3364 696

15 43 225 1849 645

9 74 81 5476 666

6 81 36 6561 486

TOTAL 57 516 579 39898 3751

Kimaro_Novat_MU-MCC 350
REGRESSION AND CORRELATION ANALYSIS

(a) 𝑋 = 57, 𝑌 = 516, 𝑋 2 = 579, 𝑌 2 = 39898 & 𝑋𝑌 =

3751

𝑛( 𝑋𝑌)−( 𝑋)( 𝑌)
(b) 𝑟 =
𝑛 𝑋 2− 𝑋 2 𝑛 𝑌2− 𝑌 2

7 3751 −(57)(516)
=
7(579)− 57 2 7(39898)− 516 2

Kimaro_Novat_MU-MCC 351
REGRESSION AND CORRELATION ANALYSIS

−3155
=
10476120
= −0.97476321424
(a)Basing on r= −0.97 is show that there is a
strong negative correlation between job stress
and employee performance.

Kimaro_Novat_MU-MCC 352
REGRESSION AND CORRELATION ANALYSIS

QUESTION
1. For the following data, find the product
moment correlation coefficient and interpret it.

Kimaro_Novat_MU-MCC 353
REGRESSION AND CORRELATION ANALYSIS

2. Compute product-moment correlation

coefficient from the following data and interpret
the result.

Kimaro_Novat_MU-MCC 354
REGRESSION AND CORRELATION ANALYSIS

Charles Spearman’s Coefficient of Correlation

• Charles Spearman’s coefficient of correlation (or
rank correlation) is the technique of determining
the degree of correlation between two variables
in case of ordinal data where ranks are given to
the different values of the variables.

Kimaro_Novat_MU-MCC 355
REGRESSION AND CORRELATION ANALYSIS

• This coefficient is determined as under;

6 𝑑2
•𝜌 = 1 −
𝑛 𝑛2 −1
• Where 𝑑 = difference between ranks of ith pair
of the two variables;
• n = number of pairs of observations.
• −1 ≤ 𝜌 ≤ 1
Kimaro_Novat_MU-MCC 356
REGRESSION AND CORRELATION ANALYSIS

• Examples
1. Two competitors rank the eight photographs in a
competition as follows;

Calculate Spearman’s coefficient of rank correlation for

the data (note the data are ranked).
Kimaro_Novat_MU-MCC 357
REGRESSION AND CORRELATION ANALYSIS

• Solution: Consider the table below.

Kimaro_Novat_MU-MCC 358
REGRESSION AND CORRELATION ANALYSIS

6 𝑑2
𝜌 =1−
𝑛 𝑛2 −1
6(30)
𝜌 =1−
8 82 −1
• 𝜌 = 0.64(2𝑑𝑝) Indicating some positive
correlation between the competitors

Kimaro_Novat_MU-MCC 359
REGRESSION AND CORRELATION ANALYSIS

2. The marks of 10 pupils in Math's and Statistics

tests are as follows;

• Calculate Spearman’s coefficient of rank

correlation.

Kimaro_Novat_MU-MCC 360
REGRESSION AND CORRELATION ANALYSIS

• Solution:Let 𝑑 = 𝑟𝑎𝑛𝑘 𝑥 − 𝑟𝑎𝑛𝑘𝑦

Kimaro_Novat_MU-MCC 361
REGRESSION AND CORRELATION ANALYSIS

• 𝑑 2 = 62 n= 10
6 𝑑
•𝜌 = 1 − 2
𝑛 𝑛 −1
6(62)
•𝜌 = 1 −
10 100−1
• 𝜌 =0.62(2 d.p)
• Spearman's coefficient of rank correlation is 0.62,
indicating some positive correlation between the
marks in two tests.
Kimaro_Novat_MU-MCC 362
REGRESSION AND CORRELATION ANALYSIS

Qns:1.The marks of eight candidates in ECO and ICT

are:

• Rank the results and hence find a rank correlation

coefficient between the two sets of marks.

Kimaro_Novat_MU-MCC 363
REGRESSION AND CORRELATION ANALYSIS

Regression Analysis
• Regression is the determination of a statistical
relationship between two or more variables.
• Regression can only interpret what exists
physically i.e., there must be a physical way in
which independent variable X can affect
dependent variable Y.
Kimaro_Novat_MU-MCC 364
REGRESSION AND CORRELATION ANALYSIS

• The basic relationship between X and Y is given by

𝒀 = a + bX where the symbol 𝑌 denotes the estimated
value of Y for a given value of X.
• This equation is known as the regression equation of
Y on X which means that each unit change in X
produces a change of b in Y, which is positive for
direct and negative for inverse relationships.

Kimaro_Novat_MU-MCC 365
REGRESSION AND CORRELATION ANALYSIS

• In order to determine the unknown parameters on the

regression model use the least square method.
• The method of least squares calculates the line of
best fit by minimizing the sum of the squares of the
vertical distances of the points to the line
• The goal of Least-Squares Method is to find a good
estimation of parameters that fit a function, 𝑓 𝑥 , of
a set of data 𝑥1 … 𝑥𝑛

Kimaro_Novat_MU-MCC 366
REGRESSION AND CORRELATION ANALYSIS

• The Least-Squares Method requires that the

estimated function has to deviate as little as
possible from 𝑓 𝑥 in the sense of a 2-norm.
• To fit a set of data best, the least-squares
method minimizes the sum of squared residuals
(it is also called the Sum of Squared Errors, SSE.)

Kimaro_Novat_MU-MCC 367
REGRESSION AND CORRELATION ANALYSIS

𝑛 2 2
•𝑆 = 𝑖=1 𝑟𝑖 , with 𝑟𝑖 the residual, which is the
difference between the actual points and the
regression line, and is defined as
• 𝑟𝑖 = 𝑦𝑖 − 𝑓 𝑥𝑖 where the m data pairs are
𝑥𝑖 , 𝑦𝑖 and the model function is 𝑓 𝑥𝑖 .
• At here, we can choose n different parameters
for 𝑓 𝑥𝑖 so that the approximated function can
best fit the data set.
Kimaro_Novat_MU-MCC 368
REGRESSION AND CORRELATION ANALYSIS

• For example, in the below graph,

2 2 2 2
• 𝑅3 = 𝑌3 − 𝑓 𝑋3 and 𝑅1 + 𝑅2 + 𝑅3 + 𝑅4 +
2
𝑅5 , the sum of the square of each red line's
length, is what we want to minimize.

Kimaro_Novat_MU-MCC 369
REGRESSION AND CORRELATION ANALYSIS

Kimaro_Novat_MU-MCC 370
REGRESSION AND CORRELATION ANALYSIS

• Linear Least-Squares (LLS) Method assumes that the

data set falls on a straight line.
• Therefore, 𝑦 = 𝑎𝑥 + 𝑏 where 𝑎 and 𝑏 are constants.
• However, due to experimental error, some data
might not be on the line exactly.
• There must be error (residual) between the
estimated function and real data
Kimaro_Novat_MU-MCC 371
REGRESSION AND CORRELATION ANALYSIS

• Linear Least-Squares Method defined the best-

fit function as the function that minimizes.
𝑖=𝑛 2
•𝑆= 𝑖=1 𝑦𝑖 − 𝑎𝑥𝑖 + 𝑏
𝜕𝑆 𝜕𝑆
• To minimize ,the conditions: = 0 and =0
𝜕𝑎 𝜕𝑏
must be satisfied.

Kimaro_Novat_MU-MCC 372
REGRESSION AND CORRELATION ANALYSIS

𝜕𝑆 𝑖=𝑛
• = −2 𝑖=1 𝑥𝑖 𝑦𝑖 − 𝑎𝑥𝑖 + 𝑏
𝜕𝑎
𝜕𝑆 𝑖=𝑛
• =2 𝑖=1 𝑦𝑖 −
𝑎𝑥𝑖 + 𝑏
𝜕𝑏
• Expanding and dropping subscripts for simplest in
the above
𝜕𝑆
• = −2 𝑥𝑦 + 2 𝑥(𝑎𝑥 + 𝑏) = 0
𝜕𝑎
𝜕𝑆
• =2 𝑦-2a 𝑥 + 2 𝑏=0
𝜕𝑏
Kimaro_Novat_MU-MCC 373
REGRESSION AND CORRELATION ANALYSIS

𝜕𝑆 2
• =− 𝑥𝑦+𝑎 𝑥 +𝑏 𝑥=0
𝜕𝑎
𝜕𝑆
• = 𝑦 −a 𝑥 − 𝑏=0
𝜕𝑏
𝑥𝑦 = 𝑎 𝑥 2 + 𝑏 𝑥 …………………….. (i)
𝑦=a 𝑥 + 𝑏𝑛…………………………….. (ii)

Kimaro_Novat_MU-MCC 374
REGRESSION AND CORRELATION ANALYSIS

• If the least squares regression line is 𝑦 on 𝑥 then

𝑦 = 𝑎𝑥 + 𝑏, then values of 𝑎 and 𝑏 are found by
solving the simultaneous equations (i) and (ii).
• These equations are called the normal
equations for 𝒚 on 𝒙.

Kimaro_Novat_MU-MCC 375
REGRESSION AND CORRELATION ANALYSIS

• If the least square regression line is 𝑥 on 𝑦 then

𝑥 = 𝑎𝑦 + 𝑏 and the normal equations will become
2
𝑥𝑦 = 𝑎 𝑦 + 𝑏 𝑦 …………………….. (i)
𝑥 =a 𝑦 + 𝑏𝑛…………………………….. (ii)

Kimaro_Novat_MU-MCC 376
REGRESSION AND CORRELATION ANALYSIS

• Example
1. Determine the line of best fit of 𝑦 on 𝑥 from
the following data.

Kimaro_Novat_MU-MCC 377
REGRESSION AND CORRELATION ANALYSIS

Kimaro_Novat_MU-MCC 378
REGRESSION AND CORRELATION ANALYSIS

2
• 𝑥𝑦 = 495 , 𝑥 = 270, 𝑥 = 38,
𝑦 = 89, 𝑛 = 7
2
𝑥𝑦 = 𝑎 𝑥 + 𝑏 𝑥
𝑦=a 𝑥 + 𝑏𝑛
• 495 = 270a + 38b … … … … eqn (i)
• 89 = 38𝑎 + 7𝑏 … … … … … . . 𝑒𝑞𝑛 (𝑖𝑖)
• Solving eqns simultaneously
Kimaro_Novat_MU-MCC 379
REGRESSION AND CORRELATION ANALYSIS

• 𝑎 ≈ 0.186 and 𝑏 ≈ 11.704

• From 𝑦 = 𝑎𝑥 + 𝑏 then;
• 𝑦 = 0.189𝑥 +11.704

Kimaro_Novat_MU-MCC 380
REGRESSION AND CORRELATION ANALYSIS

2. Estimate the regression line of yield on

temperature.

Kimaro_Novat_MU-MCC 381
REGRESSION AND CORRELATION ANALYSIS

• Let 𝑥 be temperature and 𝑦 be yields.

Kimaro_Novat_MU-MCC 382
REGRESSION AND CORRELATION ANALYSIS

2
• 𝑥𝑦 = 3502 , 𝑥 = 140000, 𝑥 = 980,
𝑦 = 24.6, 𝑛 = 7
By normal equations:
• 3502 = 140000a + 980b … … … … eqn (i)
• 24.6 = 980𝑎 + 7𝑏 … … … … … . . 𝑒𝑞𝑛 (𝑖𝑖)
Solving simultaneously
Kimaro_Novat_MU-MCC 383
REGRESSION AND CORRELATION ANALYSIS

• 𝑎 ≈ 0.021 and 𝑏 ≈ 0.614

• From 𝑦 = 𝑎𝑥 + 𝑏 then; 𝑦 = 0.021𝑥 +0.614
• Thus; 𝑦𝑖𝑒𝑙𝑑𝑠 = 0.021𝑡𝑒𝑚𝑝𝑒𝑟𝑎𝑡𝑢𝑟𝑒 + 0.614

Kimaro_Novat_MU-MCC 384
REGRESSION AND CORRELATION ANALYSIS

• Qns: Assume that you in charge of the Central

Bank(BOT).You are given the following
information on macro economic variable,
quantity of money(M) and Gross Domestic
Product(GDP) in million(Tshs).

Kimaro_Novat_MU-MCC 385
REGRESSION AND CORRELATION ANALYSIS

Kimaro_Novat_MU-MCC 386
REGRESSION AND CORRELATION ANALYSIS

a) Plot these data on a scatter diagram. What

does the scatter diagram reveals? Estimate
the regression of national income on the
quantity of money.
b) If you had a sole control over money supply
and wished to achieve a level of national
income of 12.0 in 2000, at what level you set
the money supply?
Kimaro_Novat_MU-MCC 387
REGRESSION AND CORRELATION ANALYSIS

QN: In a study of 5 industrial areas, a researcher

obtained these data relating the average number
of units of a certain pollutant in the air and the
incidence (per 100,000 people) of a certain
disease.

Kimaro_Novat_MU-MCC 388
REGRESSION AND CORRELATION ANALYSIS

a) Plot these data on a graph

b) Find the equation of the least square
c) Use it to estimate the incidence of the disease
in an area with an average pollution level of
7.3 units

Kimaro_Novat_MU-MCC 389
REGRESSION AND CORRELATION ANALYSIS

A company’s annual sales (in units of 1 billion

dollars) for its first 5years of operation are shown
in the table.

Kimaro_Novat_MU-MCC 390
REGRESSION AND CORRELATION ANALYSIS

a) Plot these data on the graph

b) Find the equation of the least square line.
c) Use it to predict the company’s 6th year sales.

Kimaro_Novat_MU-MCC 391
REGRESSION AND CORRELATION ANALYSIS

QN: To test effect of a new drug twelve patients

were examined before the drug was administered
and given an initial score (I) depending on the
severity of various symptoms. After taking the
drug they were examined again and given a final
score (F). A decrease in score represented an
improvement. The scores for the twelve patients
are given in table below.
Kimaro_Novat_MU-MCC 392
REGRESSION AND CORRELATION ANALYSIS

Kimaro_Novat_MU-MCC 393
REGRESSION AND CORRELATION ANALYSIS

a) Calculate the equation of the line of

regression of F on I.
b) On average what improvement would you
expect for a patient whose initial score was
30?

Kimaro_Novat_MU-MCC 394