Chapter 7

• Measurmenet & Scaling

 Chapter outline

1) Overview

2) Measurement and Scaling

3) Primary Scales of Measurement

i. Nominal Scale : classification :

ii. Ordinal Scale : Ranking

iii. Interval Scale : Equal intervals

iv. Ratio Scale :

4) A Comparison of Scaling Techniques)
5) Non comparative Scaling Techniques
 .

Measurement
 Measurement : is the process of observing and recording the
observation that are collected as part of research.
 The recording of the observation may be in terms of numbers or other
symbols to characteristics of objects according to certain prescribed
rules.
 The respondents characteristics are feelings, attitudes, opinions etc.
 The most important aspect of measurement is the specification of rules
for assigning numbers to characteristics
 The rules for assigning numbers should be standardized and applied
uniformly.
 This must not change over time or objects.

 We measure not the object but some characteristic of it. Thus, we do

not measure consumers, only their perceptions, attitudes, preferences
or other relevant characteristics.
 Variable
• When we measure the attributes of an object, we

obtain a value that varies between objects.

• For example consider the people in this class as

objects and their height as the attribute

• The attribute height varies between objects, hence

attributes are more collectively known as variables

• Variables can be measured on four different scales

 Measurement and Scaling
 Scaling involves creating a continuum upon which

measured objects are located.

 Consider an attitude scale from 1 to 100. Each

respondent is assigned a number from 1 to 100, with 1
= Extremely Unfavorable, and 100 = Extremely
Favorable.

 Measurement is the actual assignment of a number

from 1 to 100 to each respondent.

 Scaling is the process of placing the respondents on a

 Levels of measurement scales /Method of
assigning numbers

• Level of measurement refers to the relationship among

the values that are assigned to the attributes ,feelings or
opinions for a variable

• There are 4 levels of measurement scales or methods of

assigning numbers.

1. Nominal scale/Categorizing

2. Ordinal scale/ Ranking

3. Interval scale/ Determination of the size interval

4. Ratio scale/ Determination of the size of ratios

 Measurement Scales

• .
Nonmetric Metric

Nominal Ordinal Interval Ratio

 Primary Scales .of Measurement
Scale
Nominal Numbers Finish
• . Assigned
7 8 3
to Runners

Ordinal Rank Order Finish

of Winners
Third Second First
place place place

Interval Performance
Rating on a 8.2 9.1 9.6

0 to 10 Scale
15.2 14.1 13.4
Ratio Time to
Finish, in
 Nominal Scale

 Classifies data according to a category only.

 E.g., which color people select.

 Colors differ qualitatively not quantitatively.

 A number could be assigned to each color, but it would

not have any value.

 The number serves only to identify the color.

 No assumptions are made that any color has more or

less value than any other color.

 .
• Nominal: observations are put into categories based on
some criterion
• Classifies; categorizes

• Dichotomous Variable: has two values; e.g. male/female,

yes/no
• Multichotomous: has more than two values; e.g. ethnicity,
marital status
 Only present percentages of categories

 Chi-square most often used test of statistical

significance
 Examples .

Gender ( ) Female ( ) Male

Marital Status ( ) Married ( ) Single ( ) Divorced
Nationality ( ) Ethiopian ( ) Arab ( ) Germen ( ) English

 Percentage of the numbers can be calculated

- 40% Male and 60% Female

• Which of the following media influences your purchasing decisions the

most?

– 1 Television

– 2 Radio

– 3 Newspapers
- Mode , cross tabulation , chi-square ,
.
frequencies can be calculated

•Table
. 1: The Nationality of the Tourists

Nationality Ferquency (%)

Ethiopian 330 21
Germeny 610 38
Japanies 560 35
Arab 100 06
Total 1600 100
 Ordinal Scale
.
classifies nominal data
according to some order or
• .
rank E.g. names ordered
alphabetically
With ordinal data, it is fair to
say that one response is
greater or less than another.
E.g. if people were asked to
rate the hotness of 3 chili
peppers, a scale of "hot",
"hotter" and "hottest" could be
used. Values of "1" for "hot", The gap between the items is
"2" for "hotter" and "3" for unspecified.
"hottest" could be assigned.
 .

 Can include opinion and preference scales

 Median but not mean

 No unique, arithmetic origin

 Means items cannot be added

 In marketing research practice, ordinal scale variables are
often treated as interval scale variables
Examples
 GPA
 Small , medium , large
 Quality
 Likert scales, rank on a scale of 1..5 your degree of
satisfaction
 Women’s dress sizes
 .
• Common examples of ordinal scales include quality rankings, rankings of

teams in a tournament and occupational status. In marketing research,

ordinal scales are used to measure relative attitudes, opinions, perceptions
and preferences.

• Measurements of this type include ‘greater than’ or ‘less than’ judgments

from the respondents.

• Ordinal data would be used

median,

rank order correlation

•
 Interval scale

• In an interval scale, numerically equal distances on

the scale represent equal values in the characteristic
being measured because it is metric.

• An interval scale contains all the information of an

ordinal scale, but it also allows you to compare the
differences between objects.

• The difference between any two scale values is

identical to the difference between any other two
adjacent values of an interval scale.
 .
• There is a constant or equal interval between
scale values. The difference between 1 and 2 is
the same as the difference between 2 and 3,
which is the same as the difference between 5
and 6.
• A common example in everyday life is a
temperature scale. In marketing research,
attitudinal data obtained from rating scales are
often treated as interval data.
• Interval is a metric scale, so it is possible to
calculate the arithmetical means of interval scale.
Interval scale can be five, seven or nine-level scale
• Ethiopian people are generous.
(5) Strongly agree
(4) Agree
(3) Neither agree nor disagree
(2) Disagree
(1) Strongly disagree
• Let us assume that 200 students have
answered the question. above as follow,
calculate the arithmetical means
Participation Degree Frequency %
5 Strongly agree 75 37.5
4 64 32
3 38 19
2 18 9
1 Strongly disagree 5 2.5
Total 200 100

The weighted arithmetic means is?

(5x0.375)+(4x0.32)+(3x0.19)+(2x0.09)+(1x
0.025)=3.93
 .

• Interpretation of the result:

• The arithmetical means (the average) of the
population is 3.93 which it means that the
population almost agree that they are proud of
their country.
•
 Ratio scale
• A ratio scale possesses all the properties of the
nominal, ordinal and interval scales, and in
addition, an absolute zero point.
• Thus, in ratio scales we can identify or classify
objects, rank the objects, and compare intervals
or differences. It is also meaningful to compute
ratios of scale values.
 .

• In marketing, sales, costs, market share and

number of customers are variables measured on a
ratio scale.
• In Economics income, inflation rate, exchange
rate, population, income per capita etc. are good
examples of ratio scale.
 .

All measurements together

 Measurement scales

• The various types of scales used in research fall

into two broad categories: comparative and non

comparative.

• In comparative scaling, the respondent is asked to

compare one brand or product against another.

• With noncomparative scaling respondents need

only evaluate a single product or brand.

• Their evaluation is independent of the other

product and/or brands which the researcher is

 A Classification of Scaling Techniques
• . Scaling Techniques

Comparative Noncomparative
Scales Scales

Paired Rank Continuous Itemized

Constant Sum
Comparison Order Rating Scales Rating Scales

Semantic Stapel
Likert
Differential
 .

• Comparative scales involve the direct comparison of

stimulus objects.
• Comparative scale data must be interpreted in relative
terms and have only ordinal or rank order properties.

e.g. How does Pepsi compare with Coke on sweetness

• In noncomparative scales, each object is scaled
independently of the others in the stimulus set.
• The resulting data are generally assumed to be interval
or ratio scaled.

• e.g. How would you rate the sweetness of Pepsi on a scale of

1 to 10
 Paired Comparison Scaling
• A respondent is presented with two objects and
asked to select one according to some criterion.
• The data obtained are ordinal in nature.
• Paired comparison scaling is the most widely used
comparative scaling technique.
• Under the assumption of transitivity, it is possible
to convert paired comparison data to a rank
order.
 Method of paired comparisons
Under it the respondent can express his attitude by making a choice between two

objects, say between a new flavor of soft drink and an established brand of

drink.

But when there are more than two stimuli to judge, the number of judgements

required in a paired comparison is given by the formula:

N= n (n-1)/2

where

N = number of judgements

n = number of stimuli or objects to be judged.

• For instance, if there are ten suggestions for bargaining proposals available to a

workers union, there are 45 paired comparisons that can be made with them.

• When N happens to be a big figure, there is the risk of respondents giving ill
 Rank Order Scaling
• Respondents are presented with several objects
simultaneously and asked to order or rank them
according to some criterion.
• It is possible that the respondent may dislike the
brand ranked 1 in an absolute sense.
• Furthermore, rank order scaling also results in
ordinal data.
 .

• Example: 10 consumers asked to rank 4

different brands by severity, from most
important to less important
Consumers A B C D
1. Consumer 2 1 3 4
2. Consumer 1 2 4 3
3. Consumer 2 1 3 4
4. Consumer 4 2 1 3
5. Consumer 3 1 2 4
6. Consumer 2 1 3 4
7. Consumer 1 3 2 4
8. Consumer 4 2 1 3
9. Consumer 2 1 4 3
10.Consumer 3 1 4 2

………………………….. ranks first

 The classification of the Data

Brands First Second Third Fourth

A 2 4 2 2
B 6 3 1 0
C 2 2 3 3
D 0 1 4 5

Given 4 point to be first, 3 points to be

second, 2 points to be third and 1 point to be
fourth, we can calculate the weight of
preference for each brand.
 .

It is easy to say that brand B ranks first, A ranks

second, C ranks third and D ranks last. Therefore,
B>A>C>D

Calculating the distance among the brands also is

possible
Between B & A 35-26 = 9 Units
Between A & C 26-23 = 3 Units
Between C & D 23-16 = 7 Units
 Constant sum scaling
• In constant sum scaling, respondents allocate a constant sum of
units, such as points, among a set of stimulus objects with
respect to some criterion.
Example
• Below are three attributes of four supermarkets. Please allocate
100 points among the attributes so that your allocation reflects
the relative importance you attach to each attribute.
• The more points an attribute receives, the more important an
attribute is.
• If an attribute is not at all important, assign it no points. If an
attribute is twice as important as some other attribute, it should
receive twice as many points.
• .
 Average Points of Evaluating 4 Supermarkets By 3 Criteria

Brands Criteria
Staff Product
Behavior Cheapness Assortment Total

A Market 30 40 40 110
B Market 40 10 40 90
C Market 10 20 5 35
D Market 20 30 15 65
Total 100 100 100

It is clear that supermarket A ranks first then market B

then D and finally C
 Non-comparative Scaling Techniques

• Respondents using a non-comparative scale

employ whatever rating standard seems
appropriate to them.
• They do not compare the object being rated
either with another object or to some specified
standard, such as ‘your ideal brand’. They evaluate
only one object at a time.
 Continuous rating scale
• Continuous rating scales: The respondents are asked to give a
rating by placing a mark at the appropriate position on a
continuous line.
• The scale can be written on card and shown to the respondent
during the interview.
• How would you rate Marketing Research to
• .
other courses this term

• The worst x--------------------------x The best

10 20 30 40 50 60 70 80 90 100
 .

How would you evaluate our Hotel?

How do you compare Coca Cola with Pepsi Cola?

Totally Totally
Different Same
.
 Itemized Rating
. Scales

• .
Semantic The Likert scale Staple scale
Differential
Scale
 Likert scale

• is a widely used rating scale that requires the

respondents to indicate a degree of agreement or
disagreement with each of a series of statements
about the stimulus objects.

• Typically, each scale item has five response

categories, ranging from ‘strongly disagree’ to
‘strongly agree’.

• Likert scale is not a kind of question. It is a scale which measures

an attitude or behavior.
Example
 .

• .
FREQUENCY

• Very Frequently • Always • Always

• Frequently • Very Frequently • Almost Always
• Usually
• Occasionally • Occasionally • To a Considerable Degree
• About Half the Time
• Rarely • Rarely • Occasionally
• Seldom
• Very Rarely • Very Rarely • Seldom
• Never
• Never • Never

• A Great Deal • Always

• Often
• Much • Very Often
• Sometimes
• Somewhat • Sometimes
• Seldom
• Little • Rarely
• Never
• Never • Never
IMPORTANCE

• Very Important
.
• Important
• Moderately Important • Very Important
• . • Of Little Importance • Moderately Important
• Unimportant • Unimportant

QUALITY

• Very Good • Extremely Poor

• Good • Below Average • Good
• Barely Acceptable • Average • Fair
• Poor • Above Average • Poor
• Very Poor • Excellent
 .
LIKELIHOOD
• .
• To a Great Extent
• Like Me • Somewhat • True
• Unlike Me • Very Little • False
• Not at All

• Almost Always True

• Definitely • Usually True • True of Myself
• Very Probably • Often True • Mostly True of Myself
• Probably • Occasionally True • About Halfway True of Myself
• Possibly • Sometimes But Infrequently True • Slightly True Of Myself
• Probably Not • Usually Not True • Not at All True of Myself
• Very Probably Not • Almost Never True
 Semantic differential scale
• The semantic differential is a seven-point rating scale
with end points associated with bipolar labels that have
semantic meaning.

• This type of scale makes extensive use of words rather

than numbers.

• Respondents describe their feelings about the products

or brands on scales with semantic labels.

• When bipolar adjectives are used at the end points of

the scales, these are termed semantic differential scales.
 .

• .
 Stapel scale
• Stapel, is a unipolar rating scale with 10 categories

numbered from –5 to +5, without a neutral point

(zero).

• This scale is usually presented vertically

• Respondents are asked to indicate by selecting an

appropriate numerical response category how

accurately or inaccurately each term describes the
object.

• The higher the number, the more accurately the term

describes the object.

Staple Scale .
The following questions concern your ratings of several suppliers that provide
products for use in your store.
• .
XYZ
Poor Product -5 -4 -3 -2 -1 1 2 3 4 5
Selection

Costly Products -5 -4 -3 -2 -1 1 2 3 4 5

Fast Service -5 -4 -3 -2 -1 1 2 3 4 5

High Quality -5 -4 -3 -2 -1 1 2 3 4 5
Products

Innovative -5 -4 -3 -2 -1 1 2 3 4 5
 Choosing the Appropriate Scale

Attitude
component
Itemized
category
Rank
order .Constant
sum
Likert Semantic
differential
Knowledge
• .
Awareness A
Attribute beliefs A B B B A
Attribute A B A B
importance
Affect or Liking
Overall A B A B B
preferences
Specific A B B B A
attributes
Action
intentions A B A B

A = Very appropriate, B = Sometimes appropriate

 .
Characteristics of Good Measurement Scales
1. Reliability
• The degree to which a measure accurately captures an individual’s true outcome
without error; Accuracy

synonymous with repetitive consistency

 A measure is reliable when different attempts atmeasuring something converge

on the same result

 Think of a scale to measure weight. You would expect this scale to be consistent
from one time to the next.

2. Validity

• The degree to which a measure faithfully represents the underlying concept;

Fidelity

• Are we accurately measuring what we think we are measuring ?

3. Sensitivity

• The ability to discriminate meaningful differences between attitudes. The more

 Validity and Reliability

 Reliability refers to the extent to which a scale produces

consistent results if repeated measurements are made
 If a measure is valid, then it is reliable

 If it is not reliable, it can not be valid

 If it is reliable, it may or may not be valid

 Reliability can be more easily determined than validity

 Discussion Questions

1. Distinguish level of scale measurement

2. Discuss the criteria for good measurement
3. Provide a basic assessment of scale reliability and
validity
4. Discuss Non-comparative and comparative scales
with examples
 .

Have a
lucky day