CHAPTER 5 : IDENTIFYING VARIABLES
RES EARCH METHODOLOGY (
1
Topic Learning Outcomes
At the end of this lecture, students should be able to;
• differentiate between a concept and a variable.
• convert concepts into variables.
• identify types of variables.
• identify types of measurement scales.
• define hypothesis and its function in research.
• demonstrate how hypotheses are tested and formulated
• list different types of hypotheses and their applications
• explain how errors in the testing of a hypothesis can occur
2
What is variable
Types of variable
An image, perception or concept that is capable of CHAPTER 5
measurement- hence capable of taking on different Identifying Variables
values.
Concept that can be measured.
Causal Relationship
The difference between a concept and a variable Unit of
to investigate a causal relationship Study design
Measurability is the main difference between a concept and a or association,4 sets of variables measurement
may operate:-
variable
Independent Variables
1. Concepts -- Concepts are mental images or perceptions Active variables Quantitative
the cause supposed to be
responsible for bringing about those variables that can variables
Subjective impression change(s) in a phenomenon or be manipulated, changed
No uniformity situation. or controlled
As such cannot be measured Continuous
Dependent Variables
E.g : Effectiveness, Satisfaction, Impact, Excellent, High achiever, variables
Attribute variables
outcome or change(s) brought about
by introduction of an independent those variables that cannot be
2. Variables -- Variables are measurable variable. manipulated, changed or
controlled, and that reflect the Quantitative
Measurable though the degree of precision varies from scale to Extraneous Variables characteristics of the study variables
population. e.g: age, gender
scale and from variable to variable (e.g. attitude – subjective, several other factors operating in a
income – objective) real-life situation may affect Categorical or discrete
changes in the dependent variable.
variables
E.g: gender, attitude, age, income, weight, height, religion
-- measured on nominal or
Intervening Variables
ordinal measurement scales
it links the independent and D.V. In
Types of measurement scale certain situations the relationship
between an independent and a D.V
Stevens has classified the different types of measurement scale into 4 cannot be established without the
Constants Dichotomies Polychromies
categories: intervention of another variable.
has only two categories. can be divided into more
has only one category
E.g:male/female,yes/no, than 2 categories, e.g:
*Nominal or classificatory scale *Ordinal or ranking scale or value. E.g: taxi, tree
good/bad religion, political parties,
*Interval scale *Ratio scale
What is variable?
• A rational units of analysis that can assume any one of a
number of designated sets of values.
• A concept that can be measured on any one of the four types of
measurement scales, which have varying degrees of precision in
measurement.
4
What is a Variable and Concept in a Research Study?
A variable is an image,
perception or concept
that is capable of
measurement is called
a variable(gender, age,
income, weight, height
etc.)
A concept cannot be
measured.
(Effectiveness, impact,
satisfaction, domestic
violence)
Kumar(2014)
Converting concepts into variables
Concepts Indicators Variables
• Operationalization – how the concept will be measured?
– Process of identifying indicators
• Indicators – a set of criteria reflective of the concept,
which can then converted into variables
6
Converting concepts into variables (cont.)
• Example 1
VARIABLES
CONCEPTS INDICATORS
VARIABLES DECISION LEVEL
Wealth 1. Income 1. Total income per 1 if > RM 150,000
2. Assets year 2 if > RM 300,000
2. Total values of home, cars,
boats, investments
7
Converting concepts into variables (cont.)
• Example 2
VARIABLES
CONCEPTS INDICATORS
VARIABLES DECISION LEVEL
High 1. Average marks 1. Percentage of marks 1 if > 70%
academic obtained in 2. Percentage of marks 2 if > 80%
achieve- exam 3. Percentage of marks 3 if > 90%
ment 2. Average marks
obtained in
practical
3. Aggregate
marks
8
Converting concepts into variables (cont.)
• Example 3
VARIABLES
CONCEPTS INDICATORS
VARIABLES DECISION LEVEL
Effective- 1. Changes in 1. Changes in weight in Whether the difference in
ness of nutritional the past 3 months before- and-after levels is
health status (weight) 2. Changes in morbidity type statistically significant
program 2. Changes in
nutritional Point prevalence increase
status or decrease in each
(morbidity) variable
9
.
The following table suggests how you might operationalise the concept of ‘effectiveness’, in relation to a health
education programme on AIDS. It lists the indicators of effectiveness (you can have other indicators), sets out the
variables that measure the indicators and describes the unit of measurement for the variables.
Concept Indicator Variable(s) Unit of measurement
Effectiveness Awareness of AIDS Extent of change in: Change in the proportion of the
population, before and after the health
education programme, with respect to:
Knowledge about AIDS Awareness Awareness of, and knowledge about,
Knowledge practice different aspects of AIDS
Use of contraceptives (practice) Use of contraceptives for safe sex
Step VIII: Operationalise your concepts.
Objectives/research Major concepts Indicators Variables Unit of
questions/hypotheses measurement
Types of variable
Cause
Model
Variables
Unit of
Study
Measure-
Design
ment
12
Types of variable – Cause Model
1• Change variable (Independent Variable)
– the cause supposed to be responsible for bringing about
change(s) in a phenomenon or situation
2• Outcome variable (Dependent Variable)
– the outcome or change(s) brought about by introduction of an independent variable
Variables which affect / influence (Extraneous Variable)
3• – several factors operating in a real-life situation may affect
changes in the dependent variable
Connecting or linking variables (Intervening Variable)
4• – confounding variables which links independent and dependent
variable
13
Types of variable – Cause Model (cont.)
1 2
14
Types of variable – Cause Model (cont.)
1 2
3
15
Types of variable – Cause Model (cont.)
1 2
3 12
SCHOOLOFNUTRITIONANDDIETETICS•UNIVERSITISULTANZAINA LABIDIN
Types of variable – Study Design
1• Active Variable
– those variable that can be manipulated, changed or
controlled.
2• Attribute Variable
– those variables that cannot be manipulated, changed or controlled and
that reflect the characteristics of the study population e.g. age, gender,
education and income
Types of variable – Study Design (cont)
1 2
Types of variable – Unit of Measurement
1• Categorical Variable – measured in nominal or ordinal measurement
scales
– Constant variable – has only one category or value
– Dichotomous – has only two categories
– Polychotomous – can be divided into more than two
categories
2•
Continuous Variable – measured in interval or ratio
scale
– have continuity in their measurement
Types of measurement scales
Nominal or
classificatory Ordinal or
scale ranking scale
Interval scale Ratio scale
Types of measurement scales - nominal
• Each subgroup has a characteristics/ property which is common to all
classified within that subgroup.
• Example;
– Gender – Male, Female
– Marital status – Single, Married, Widowed, Divorced
– Medical history – Hypertension, Diabetes, IHD, Cancer, Obesity
– Colour – Red, Blue, Green, Yellow, Black
Types of measurement scales – ordinal
• It has the characteristics of a nominal scale e.g. Individuals, groups,
characteristics classified under a subgroup have a common
characteristics.
• Subgroups have a relationship to one another. Arranged
in ascending or descending order.
• Example;
– Income – above average, average, below average
– Obesity – underweight, normal, overweight, obese
– Likert scale – strongly disagree, disagree, neutral, agree,
strongly agree
Types of measurement scales – interval
• It has all the characteristics of an ordinal scale.
• It has a unit of measurement with an arbitrary starting
and terminating point.
• Divided into equally spaced units/ intervals.
• Example;
– Income – RM501 – RM1000, RM1001 – RM1500, RM1501 –
RM2000
– Body fat – 11% - 15%, 16% - 20%, 21% - 25%
– Age group – 31 – 40 y/o, 41 – 50 y/o, 51 – 60 y/o
Types of measurement scales – ratio
• It has all the properties of an interval scale
• It has a fixed starting point e.g. a zero point
• Example;
– Income – RM
– Age – years/ months
– Weight – kg
– Height – cm
– Physical activity – METmin/week
– Energy intake - kcal
What is hypothesis?
assumption
suspicion
statements
hunch
idea
What is hypothesis? (cont.)
• A hypothesis is a conjectural statement of the relationship
between two or more variable.
• A proposition, condition, or principle which is assumed, perhaps without belief, in
order to draw out its logical consequences, and by this method to test its accord
with facts which are known or may be determined.
• A proposition that is stated in a testable form and that predicts a particular
relationship between two (or more) variables
• Characteristics of a hypothesis;
• It is a tentative proposition
• Its validity is unknown
• In most cases, it specifies a relationship between two or
more variables.
Functions of a hypothesis
The formulation of a hypothesis provides a study with focus and tells
specific aspects of a research problem to investigate
Tells us what data to collect and what not to collect,
Tells us thereby
what data to collect
providing and to
focus what
the not to collect,
study
thereby providing focus to the study
As it provided a focus, the construction of a
As it provided a focus,
hypothesis the construction
enhances objectivityof
in aa study
hypothesis enhances objectivity in a study
Enable us to add to the formulation of theory and conclude
Enable us to add to the formulation
specifically what is trueofortheory and
what is conclude
false
specifically what is true or what is false
The process of testing a hypothesis
Formulate Collect the Analyse data
Phase I
Phase II
Phase III
your hunch or required data to draw
assumption concluison
Characteristics of a hypothesis
• A hypothesis should be simple, specific and conceptually clear.
• A hypothesis should be capable of verification.
• A hypothesis should be related to the existing body of knowledge.
• A hypothesis should be operationalisiable.
Types of hypothesis
• Research Hypothesis
– The basis of our investigation
– Four types;
• Hypothesis of difference
• Hypothesis of point prevalence
• Hypothesis of association
• Hypothesis of no difference (null hypothesis)
• Alternate Hypothesis
– Explicitly specify the relationship that will be considered as true
in case the research hypothesis proves to be wrong
– Opposite of research hypothesis
– Null hypothesis (H0) or hypothesis of no difference
Types of hypothesis
1 2
a b c d
Errors in testing a hypothesis
• Incorrect conclusion about the validity f a hypothesis may be drawn if
– The study design selected is faulty
– The sampling procedure adopted is faulty
– The method of data collection is inaccurate
– The analysis is wrong
– The statistical procedures applied are inappropriate
– The conclusion drawn are incorrect
Errors in testing a hypothesis (cont.)
• Rejection of a null hypothesis when it is true
– Type I error
• Acceptance of a null hypothesis when it is false
– Type II error
When all null hypothesis is actually;
TRUE FALSE
ACCEPT Correct decision Type II error
When your decision is to;
REJECT Type I error Correct decision
Errors in testing a hypothesis (cont.)
When all null hypothesis is actually;
TRUE FALSE
When your ACCEPT Correct decision Type II error
decision is to; REJECT Type I error Correct decision