SENG 407 –

SOFTWARE
METRICS AND
MEASUREMENT
LECTURE FOUR: MEASUREMENT
SCALES AND SCALE TYPES

Adegbola A.A. 2022/23

Introduction
 Measurement scales can be classify into the following
types
 Nominal
 Ordinal
 Interval
 Ratio
 Absolute:
Nominal Scale
 A Nominal Scale is a measurement scale, in which
numbers serve as “tags” or “labels” only, to identify or
classify an object.
 In other words, nominal scale measurement places
elements in a classification scheme. The classes are not
ordered; even if the classes are numbered from 1 to n
for identification, there is no implied ordering of the
classes.
Nominal Scale
 The nominal scale has two major characteristics
 The empirical relation system consists only of
different classes; there is no notion of ordering
among the classes.
 Any distinct numbering or symbolic representation of
the classes is an acceptable measure, but there is no
notion of magnitude associated with the numbers or
symbols.
Nominal Scale Examples
 Behavioral pattern  Hair color
E - Extroverted 1-Black
I - Introverted 2-Brown
A - Ambivert 3-Burgundy
 Gender 4-Auburn
M - Male 5-Other
F - Female
Ordinal Scale
 Ordinal scale is the measurement that reports the
ranking and ordering of the data without actually
establishing the degree of variation between them.
 The ordinal scale has the following characteristics:
 The empirical relation system consists of classes that
are ordered with respect to the attribute.
 Any mapping that preserves the ordering (i.e., any
monotonic function) is acceptable.
 The numbers represent ranking only, so addition,
subtraction, and other arithmetic operations have no
meaning.
Ordinal Scale Examples
 Class of Degree  How happy are you with
First Class the customer service?
Second Class Upper 1- Very Unhappy
Second Class Lower 2- Unhappy
Third Class 3- Neutral
4- Unhappy
 Ranking in high school
5- Very Unhappy
First Position (1st)
Second Position (2nd)
Third Position (3rd)
Nth Position
Interval Scale
 The interval scale carries more information, making it
more powerful than nominal or ordinal.
 This scale captures information about the size of the
intervals that separate the classes, so that we can in
some sense understand the size of the jump from one
class to another.
 Interval scale has the following characteristics
 An interval scale preserves order, as with an ordinal
scale.
Interval Scale
 An interval scale preserves differences but not ratios.
That is, we know the difference between any two of
the ordered classes in the range of the mapping, but
computing the ratio of two classes in the range does
not make sense.
 Addition and subtraction are acceptable on the
interval scale, but not multiplication and division.
Interval Scale Example
 Rate your programming skill on the scale of 1 – 10
rating
1 - Novice
10 - Guru
 Customer satisfaction is key to organizational growth
1 - Completely Agree
2 - Somewhat Agree
3 - Neutral
4 - Somewhat Disagree
5 - Completely Disagree
Ratio Scale
 Ratio scale is a type of variable measurement scale
which is quantitative in nature. It allows any researcher
to compare the intervals or differences
 Ratio scale possesses a zero point or character of
origin. This is a unique feature of this scale.
 For example, the temperature outside is 0-degree
Celsius. 0 degree doesn’t mean it’s not hot or cold, it is
a value.
Ratio Scale
 The ratio scale has the following characteristics
 It is a measurement mapping that preserves ordering,
the size of intervals between entities, and ratios
between entities.
 There is a zero element, representing total lack of the
attribute.
 The measurement mapping must start at zero and
increase at equal intervals, known as units.
 All arithmetic can be meaningfully applied to the
classes in the range of the mapping.
Ratio Scale Example
 What is your height in feet 1-110 kgs
and inches? More than 110 kgs
Less than 5 feet.  Select which age bracket
5 feet 1 inch – 5 feet 5 inches
do you fall in?
5 feet 6 inches- 6 feet Below 20 years
More than 6 feet. 21-30 years
 What is your weight in 31-40 years
kgs? 41-50 years
Less than 50 kgs 50 years and above
51- 70 kgs
71- 90 kgs
Absolute Scale
 An absolute scale is a system of measurement that
starts at a minimum point and the progresses in only
one direction.
 An absolute scale is a count of the elements in a set. Its
natural origin is zero, or the empty set.
 The count is the ordering (a set of five elements is
bigger than a set of three elements, and so on).
Absolute Scale
 Absolut scale has the following characteristics
 The measurement for an absolute scale is made
simply by counting the number of elements in the
entity set.
 The attribute always takes the form “number of
occurrences of x in the entity.”
 There is only one possible measurement mapping,
namely the actual count, and there is only one way to
count elements.
 All arithmetic analysis of the resulting count is
meaningful.
Absolute Scale Examples
 The most common example of this is the Kelvin scale
that measures ambient temperature from absolute zero
(the point at which molecules no longer vibrate) and
proceeds upwards into infinity.
Meaningfulness in Measurement
 Understanding scale types enables us to determine
when statements about measurement make sense
 In general, measures often map attributes to real
numbers, and it is tempting to manipulate the real
numbers in familiar ways: adding, averaging, taking
logarithms, and performing sophisticated statistical
analysis.
 We must remember that the analysis is constrained by
the scale type.
Meaningfulness in Measurement
 We can perform only those calculations that are
permissible for the given scale, reflecting the type of
attribute and mapping that generated the data.
 In other words, knowledge of scale type tells us about
limitations on the kind of mathematical manipulations
that can be performed.
 The key question we should ask after having made our
measurements is: can we deduce meaningful
statements about the entities being measured?
Meaningfulness in Measurement
 This question is harder to answer than it first appears.
To see why; consider the following statements:
1. The number of errors discovered during the
integration testing of program X was at least 100.
2. The cost of fixing each error in program X is at least
100.
3. A semantic error takes twice as long to fix a syntactic
error.
4. A semantic error is twice as complex as a syntactic
error.
Meaningfulness in Measurement
 Analyzing statement 1:
1. The number of errors discovered during the
integration testing of program X was at least 100.
Statement 1 seems to make sense
Meaningfulness in Measurement
 Analyzing statement 2:
2. The cost of fixing each error in program X is at least
100.
Statement 2 does not make sense; the number of errors
may be specified without reference to a particular
scale, but the cost of fixing an error cannot be.
Meaningfulness in Measurement
 Analyzing statement 3:
3. A semantic error takes twice as long to fix a syntactic
error.
Statement 3 seems to make sense (even if we think it
cannot possibly be true) because the ratio of time taken
is the same, regardless of the scale of measurement
used (i.e., if a semantic error takes twice as many
minutes to repair as a syntactic error, it also takes twice
as many hours, seconds, or years to repair).
Meaningfulness in Measurement
 Analyzing statement 4:
4. A semantic error is twice as complex as a syntactic
error.
Statement 4 does not appear to be meaningful, and we
require clarification. If “complexity” means time to
understand, then the statement makes sense.
But other definitions of complexity may not admit
measurement on a ratio scale; in those instances,
Statement 4 is meaningless.
Meaningfulness in Measurement
 Our intuitive notion of a statement’s meaningfulness
involving measurement is quite distinct from the notion
of the statement’s truth.
For example, the statement
The President of Nigeria is 125 years old
 Is a meaningful statement about the age measure, even
though it is clearly false.
Meaningfulness in Measurement
 We can define meaningfulness in a formal way.
We say that a statement involving measurement is
meaningful if its truth value is invariant of
transformations of allowable scales.
 We can examine the transformations to decide on
meaningfulness. Consider these statements:
Jack is twice as tall as Jill
Meaningfulness in Measurement
 This statement implies that the measures are at least
on the ratio scale, because it uses scalar multiplication
as an admissible transformation.
 The statement is meaningful because no matter which
measure of height we use (inches, feet, centimeters,
etc.), the truth or falsity of the statement remains
consistent
Meaningfulness in Measurement
 In other words, if the statement is true and if M and M’
are different measures of height, then both the
statements
M(Jack) = 2M(Jill) and
M’(Jack) = 2M’(Jill) are true.
 This consistency of truth is due to the relationship
M = aM for some positive number a.