Measrement and Scaling 08/02/2017

8-2

Chapter Outline
1) Overview
RM Module-02 2) Measurement and Scaling
3) Primary Scales of Measurement
Measurement and Scaling: i. Nominal Scale
Fundamentals and Comparative ii. Ordinal Scale
Scaling iii. Interval Scale
iv. Ratio Scale
4) A Comparison of Scaling Techniques

8/2/2017 RM by Prof Desai 1 8/2/2017 RM by Prof Desai 2

8-3 8-4

Chapter Outline Measurement and Scaling

5) Comparative Scaling Techniques Measurement
i. Paired Comparison means assigning numbers or other
ii. Rank Order Scaling symbols to characteristics of objects
iii. Constant Sum Scaling according to certain pre specified rules.
iv. Q-Sort and Other Procedures

 Examples M-15, M-20 etc. Fe-250,Fe415,Fe500

8/2/2017 RM by Prof Desai 3 8/2/2017 RM by Prof Desai 4

Research Methodology by Prof. Desai 1

Measrement and Scaling 08/02/2017

8-5 8-6

Measurement and Scaling Measurement and Scaling

 One-to-one correspondence between the numbers

and the characteristics being measured.

 The rules for assigning numbers should be Scaling

standardized and applied uniformly.
involves creating a continuum upon which
 Rules must not change over objects or time.
measured objects are located.

8/2/2017 RM by Prof Desai 5 8/2/2017 RM by Prof Desai 6

8-7 8-8
Primary Scales of Measurement
Primary Scales of Measurement Nominal Scale
Scale Figure 8.1  The numbers serve only as labels or tags for
Nominal Numbers Assigned 7 8 3 identifying and classifying objects.
to Buses, Players (useful
only for counting purposes)  When used for identification, there is a strict one-to-
one correspondence between the numbers and the
Ordinal Rank Order objects.
of Winners(Mag. Of diff. First  The numbers do not reflect the amount of the
Second
not imp/ignored/ uncertain.) place Third
place
place
characteristic possessed by the objects.
 The only permissible operation on the numbers in a
Interval Performance Rating on
nominal scale is counting.
8.2 9.1 9.6
a 0 to 10 Scale (GPA)  Only a limited number of statistics, all of which are
based on frequency counts, are permissible, e.g.,
Ratio Length, Weight, percentages, and mode.
Volume, (Time to Finish, 9.91 9.81 10.2
in Seconds ) Absolute Zero
8/2/2017 Exist. RM by Prof Desai 7 8/2/2017 RM by Prof Desai 8

Research Methodology by Prof. Desai 2

Measrement and Scaling 08/02/2017

Primary Scales of Measurement
Ordinal Scale
 A ranking scale in which numbers are assigned to
objects to indicate the relative extent to which the
objects possess some characteristic.
 Can determine whether an object has more or less of
a characteristic than some other object, but not how
much more or less.
 Any series of numbers can be assigned that
preserves the ordered relationships between the
objects.
 In addition to the counting operation allowable for
nominal scale data, ordinal scales permit the use of
statistics based on centiles, e.g., percentile, quartile,
median.
8/2/2017 RM by Prof Desai
8-9 8-10
Primary Scales of Measurement
Interval Scale
 Numerically equal distances on the scale represent
equal values in the characteristic being measured.
 It permits comparison of the differences between
objects.
 The location of the zero point is not fixed. Both the
zero point and the units of measurement are
arbitrary.
 Any positive linear transformation of the form y = a
+ bx will preserve the properties of the scale.
 It is meaningful to take ratios of scale values.
 Statistical techniques that may be used include all of
those that can be applied to nominal and ordinal
data, and in addition the arithmetic mean, standard
deviation, and other statistics commonly used in
research.
9 8/2/2017 RM by Prof Desai 10

8-11 8-12
Primary Scales of Measurement
Ratio Scale Illustration of Primary Scales of Measurement

 Possesses all the properties of the nominal, ordinal,

and interval scales. Nominal Ordinal Interval Ratio
Scale Scale Scale Scale
 It has an absolute zero point.
Preference Preference Profit
 It is meaningful to compute ratios of scale values. No. Store Rankings Ratings Earned(Lac)
1-10 1-7
 Only proportionate transformations of the form y =
1. D-Mart 7 5 9
bx, where b is a positive constant, are allowed. 2. Wall-Mart 3 7 8
 All statistical techniques can be applied to ratio data. 3. More 8 4 2
4. STAR Bazar 3 6 6
5. Big Bazar 4 7 12
6. Central Mall 5 5 15
7. City Mall 9 4 11
8. Apana Bazar 6 5 1.8
9. Z-mart 5 6 1.1
10. Reliance Store 6 2 4.5

8/2/2017 RM by Prof Desai 11 8/2/2017 RM by Prof Desai 12

Research Methodology by Prof. Desai 3

Measrement and Scaling 08/02/2017

8-13 8-14

Primary Scales of Measurement A Classification of Scaling Techniques

Scale Basic Common Engineering Permissible Statistics
Characteristics Examples Examples Descriptive Inferential
Nominal Numbers identify Adhar Card Cube No or Percentages, Chi-square, Scaling Techniques
& classify objects nos.,A/c No. Batch No. of mode binomial test
numbering RMC
players
Ordinal Nos. indicate the Quality rankings, Fondation Soil Percentile, Rank-order
relative positions rankings of teams Best, Good, median correlation, Comparative Noncomparative
of objects but not in a tournament Worst. Friedman Scales Scales
the magnitude of Cement Qality ANOVA
differences Earthqake
between them Intensity
Interval Differences Temperature Grades of Conc. Range, mean, Product-
Paired Rank Constant Q-Sort and Continuous Itemized
between objects (Fahrenheit) M-15,M-20,M50 standard moment
Ratio Zero point is fixed, Length, weight Earthquake Geometric Coefficient of Comparison Order Sum Other Rating Scales Rating Scales
ratios of scale Magnitde. mean, harmonic variation Procedures
values can be mean
compared

Semantic Stapel
Likert
8/2/2017 RM by Prof Desai 13 8/2/2017 RM by Prof Desai Differential 14

8-15 8-16

A Comparison of Scaling Techniques Relative Advantages of Comparative Scales

 Comparative scales involve the direct comparison  Small differences between stimulus objects can be
of stimulus objects. Comparative scale data must be detected.
interpreted in relative terms and have only ordinal or  Same known reference points for all respondents.
rank order properties.  Easily understood and can be applied.
 Involve fewer theoretical assumptions.
 In noncomparative scales, each object is scaled  Tend to reduce halo or carryover effects from one
independently of the others in the stimulus set. The judgment to another.
resulting data are generally assumed to be interval or
ratio scaled.

8/2/2017 RM by Prof Desai 15 8/2/2017 RM by Prof Desai 16

Research Methodology by Prof. Desai 4

Measrement and Scaling 08/02/2017

8-17 8-18
Comparative Scaling Techniques
Relative Disadvantages of Comparative Scales Paired Comparison Scaling

 Ordinal nature of the data  A respondent is presented with two objects and
 Inability to generalize beyond the stimulus objects asked to select one according to some criterion.
scaled.  The data obtained are ordinal in nature.
 Paired comparison scaling is the most widely used
comparative scaling technique.
 With n units, [n(n - 1) /2] paired comparisons are
required
 Under the assumption of transitivity, it is possible to
convert paired comparison data to a rank order.

8/2/2017 RM by Prof Desai 17 8/2/2017 RM by Prof Desai 18

8-19 8-20
Comparative Scaling Techniques
Paired Comparison Scaling Rank Order Scaling

 Respondents are presented with several objects

The most common method of taste testing is paired comparison. The simultaneously and asked to order or rank them
consumer is asked to sample two different products and select the one according to some criterion.
with the most appealing taste.
 It is possible that the respondent may dislike the
brand ranked 1 in an absolute sense.
A paired comparison
 Furthermore, rank order scaling also results in ordinal
taste test
data.
 Only (n - 1) scaling decisions need be made in rank
order scaling.

8/2/2017 RM by Prof Desai 19 8/2/2017 RM by Prof Desai 20

Research Methodology by Prof. Desai 5

Measrement and Scaling 08/02/2017

8-21 8-22
Preference for Toothpaste Brands Preference for Toothpaste Brands
Using Rank Order Scaling Using Rank Order Scaling
Figure 8.4 Figure 8.4 cont.

Instructions: Rank the various brands of toothpaste in order

Form
of preference. Begin by picking out the one brand that you like Brand Rank Order
most and assign it a number 1. Then find the second most 1. Oral-B _________
preferred brand and assign it a number 2. Continue this 2. Colgate _________
procedure until you have ranked all the brands of toothpaste 3. Dant-Kanti _________
in order of preference. The least preferred brand should be 4. Dauber _________
assigned a rank of 10.
5. Vico _________
No two brands should receive the same rank number. 6. Ultra Brite _________
7. Close Up _________
The criterion of preference is entirely up to you. There is no
right or wrong answer. Just try to be consistent. 8. Pepsodent _________
9. Plus White _________
10. Vithoba _________

8/2/2017 RM by Prof Desai 21 8/2/2017 RM by Prof Desai 22

8-23 8-24
Comparative Scaling Techniques Importance of Bathing Soap Attributes
Constant Sum Scaling Using a Constant Sum Scale

 Respondents allocate a constant sum of units, such

as 100 points to attributes of a product to reflect
their importance.
 If an attribute is unimportant, the respondent assigns
it zero points.
 If an attribute is twice as important as some other
attribute, it receives twice as many points.
 The sum of all the points is 100. Hence, the name of
the scale.
Instructions
On the next slide, there are eight attributes of
bathing soaps. 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 the attribute is. If an attribute is not at
all important, assign it zero points. If an attribute is
twice as important as some other attribute, it
should receive twice as many points.

8/2/2017 RM by Prof Desai 23 8/2/2017 RM by Prof Desai 24

Research Methodology by Prof. Desai 6

Measrement and Scaling 08/02/2017

8-25 8-26
Importance of Bathing Soap Attributes
Using a Constant Sum Scale
THANK You
Form

Attribute
Average Responses of Three Segments
Segment I Segment II Segment III Do Measure and
1. Mildness 8 2 4
2. Lather
3. Shrinkage
2
3
4
9
17
7
scale ALMIGHTY’s
4. Price 53 17 9
5. Fragrance
6. Packaging
9
7
0
5
19
9
GRACE
7. Moisturizing 5 3 20
8. Cleaning Power 13 60 15
Sum 100 100 100

8/2/2017 RM by Prof Desai 25 8/2/2017 RM by Prof Desai 26

Research Methodology by Prof. Desai 7