Variables Scales of Measurement

Variables & Scales of Measurements
Moazzam Ali
Assistant Professor
Department of English
University of Gujrat
Concepts
 Concepts are highly subjective as their understanding varies
from person to person, and therefore, may not be
measurable. In a research study it is important that the
concepts used should be operationalised in measurable terms
so that the extent of variation in respondents’ understanding
is reduced not eliminated.
 Concept is a generalized idea about a class of objects,
attributes, occurrences, or processes.
 Measurability is the main difference between a concept and a
variable. A concept cannot be measured whereas a variable
can be subjected to measurement.
Concept—an Abstraction of Reality
 Honesty, sincerity, morale are all concepts that label to some
phenomenon (reality)
 They are abstractions that exist only as mental images of things
we want to talk about. To do research, we have to convert
concepts to things we can observe. We do this by defining
concepts in terms of measurable variables.
 Measurement is a process of ascertaining the extent or quantity
of the concept, idea, or construct.
Concepts, Indicators & Variables
If you are using a concept in your study, you need to

consider its operataionalization, that is, how it will be
measured. In most cases, to operationalise a concept you
first need to go through the process of identifying
indicators—a set of criteria reflected of the concept—
which can then be converted into variables.
Variable
 Anything (concept/term) that can take on differing or varying values.
Variation can be in quantity, intensity, amount, or type.
 Examples are: Production units, Absenteeism, Gender, Religion,
Motivation, Grade, Age.
 Variables represent concepts. Like concepts, variables are defined in
words, but, as used in social research, variables have a special
characteristic. Variables have two or more observable forms or values.
 The opposite notion to a variable is a constant, which is simply a
condition or quality that does not vary between cases/subjects.The number of
cents in a United States dollar is a constant
Concepts, Indicators & Variables
Example
 The concept ‘growth of a plant’ can easily be converted into
indicators and then variables. To decide objectively if a plant is
‘growing’, one first needs to decide upon the indicators of
‘growth’.
 Example: Effect of Light & Temperature on the Growth of
Tomatoes.Variables are:
 (1) growth of tomatoes measured/operationalized in terms of
its indicators e.g. Numbers of leaves per plant, length of stem,
number of flowers per plant & yield per plant;
 (2) intensity, wavelength, frequency & color of light;
 (3) type of temperature & temperature in degrees Celsius
Concept and Variables
Concept Variable
Effectiveness Sex (male/female)
Satisfaction Income (Rs……)
Impact Age
Self esteem Height
Quality Weight
Variables and Attributes
 An attribute is a specific value on a variable. For instance, the variable
sex or gender has two attributes: male and female. Attributes are what social
scientists measure to describe a variable.
 Attributes are the observable characteristics of variable; variables are the
logical combinations of attributes. Male and female, for example, are the
attributes of the variable we call gender. The numbers of persons in a
household, from 1 to perhaps 20 or more, represent the attributes of the
variable, household. Similarly, the variable agreement might be defined as
having five attributes:
1 = strongly disagree;
2 = disagree;
3 = neutral;
4 = agree;
5 = strongly agree
Variables & Attributes
Variable Attributes
Gender Male, female
Nationality Sudanese, Zambian, Egyptian, etc.
Intelligence 120, 97, 111, 105
Management, psychology,
Student’s major
chemistry
Family size 4, 12, 6, 10, 2
Social status Low, middle, high

Types of Variables
 Independent variable is the cause supposed to be
responsible for bringing about change/s in a phenomenon or
situation. Usually, the researcher cannot manipulate the
independent variable
 Dependent variable is the outcome of the change/s
brought about by changes in an independent variable
 Extraneous variables are the several others factors
operating in real-life situation may affect changes attributed
to independent variables. These factors, not measured in the
study, may increase or decrease the magnitude or strength of
the relationship between independent and dependent
variables.
Types of Variables
 Intervening variables are sometimes called the

confounding variables. They link independent and dependent
variable. In some situations the relationship between
independent and dependent variables cannot be established
without the intervention of another variable. The cause
variable will have the assumed effect only in the presence of
an intervening variable.
Independent, Dependent and Extraneous
Variables in Causal Relationship
Independe Extraneous Intervening Dependent
ntVariable Variables Variable Variable
Age of the person
Extent of smoking
Smoking Cancer
Extent of Exercise Quality of Tobacco
(Assumed Sex (male/female) (Assumed

cause) effect)
Education
Scales of Measurements
Scales of Measurement
 Measurement (or observation) is the process of determining
and recording which of the possible traits of a variable an
individual case/subject exhibits or possesses.
 When we construct a scale of measurement we need to
follow two particular rules:
 First, the scale must capture sufficient variation to allow us to
answer our research question(s).
 Second, a scale must allow us to assign each case into one, and only
one, of the points on the scale.
Scales of Measurement: Rule I
 The scale must capture sufficient variation
Age for a group of students highlights an intrinsic problem when we try
to set up a scale to measure sufficient variation for a continuous
variable (Age) that does not arise when we try to measure a discrete
variable (Sex).
 The sex of students is a discrete variable with only two possible
categories (male or female) which cannot be subdivided and a scale can
measure its variation sufficiently. However, the age of students, on the
other hand, is a continuous variable and can be infinitely subdivided, and
hence is difficult to measure in its all possible variations .
 We will always have to ‘round off’ the measurement and treat a
continuous variable as if it is discrete. Practically, No measurement scale
can ever hope to capture the full variation expressed by a continuous
variable
Scales of Measurement: Rule II
 A scale must allow us to assign each case/subject into
one, and only one, of the points on the scale.
 This statement actually embodies two separate principles of
measurement.
 The principle of exclusiveness: No case/subject should
have more than one value for the same variable.
 The principle of exhaustiveness: Every case/subject can
be classified into a category.
Levels of Measurement
We generally talk about measurement scales having one of
four distinct levels of measurement:
1. Nominal
2. Ordinal
3. Interval
4. Ratio
Nominal Scale
 A nominal scale of measurement classifies cases into
categories that have no quantitative ordering. It simply
defines groups of the subjects. The values are given different
names, hence the term nominal.
 Example: Muslim, Hindu, Jewish, Christian
Nominal Scale
Please specify your Gender:

discipline:
 Male
 Arts  Female
 Humanities
 Pure Sciences
 Social Sciences
Ordinal Scale
 An ordinal scale of measurement, in addition to the function
of classification, allows cases to be ordered by degree
according to measurements of the variable. So, ordinal scales
enable us to rank cases. However, the difference in
property (low/medium & medium/high) or attribute
between levels may not be the same.
 Example: level of intensity –low, medium, high
 Nominal and ordinal scales are sometimes collectively called
categorical scales. However, an ordinal scale provides
additional information.
Ordinal Scale
Your income is:
□ Below 30,000
□ 30,100 to 50,000
□ 50,100 and above
Interval Scale
 An interval scale has units measuring intervals of equal distance
between values on the scale.
 Ordinal scales permit us to rank cases in terms of a variable; we
can, for example, say that one case is ‘better’ or ‘stronger’ than
another. But an ordinal scale does not allow us to say by how much
a case is better or stronger when compared with another and the
distances – intervals – between the categories are unknown.
 So, we not only can say that one case has more (or less) of the
variable in question than another, but we can also say how much
more (or less). Thus someone who is 25 years old has 7 years
more age than someone who is 18 years old; we can measure the
interval between them. Moreover, the intervals between points
on the scale are of equal value over its whole range.
Ratio Scale
 A ratio scale has a value of zero indicating cases where no quantity
of the variable is present.
 A ratio variable, has all the properties of an interval variable, and
also has a clear definition of 0.When the variable equals 0.0, there
is none of that variable.
 Notice that an observation of 0 years represents a case which
possesses no quantity of the variable ‘Years at School’. Such a
condition is known as a true zero point and is the defining
characteristic of a ratio scale, as opposed to an interval scale.
 However, heat measured in degrees Celsius does not have a ‘true’
zero. There is a zero point, but 0°C does not indicate a case where
no heat is present – it is cold but not that cold! Instead, 0°C
indicates something else: the point at which water freezes.
Levels of Measurement
Thanks

Variables Scales of Measurement

Uploaded by

Copyright:

Available Formats

Variables Scales of Measurement

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Variables Scales of Measurement

Uploaded by

Copyright:

Available Formats

Variables & Scales of Measurements

If you are using a concept in your study, you need to

Satisfaction Income (Rs……)

Self esteem Height

Gender Male, female

Nationality Sudanese, Zambian, Egyptian, etc.

Intelligence 120, 97, 111, 105

Family size 4, 12, 6, 10, 2

Social status Low, middle, high

 Intervening variables are sometimes called the

(Assumed Sex (male/female) (Assumed

Please specify your Gender:

You might also like