Measurement and Scaling in Marketing Research

1
Measurement and ScalinginMarketing Research
2
Basic Question-Response Formats

• Open-ended Presents no response options to the
  respondent
• Close-ended Provides response options on the
  questionnaire that can be answered quickly and
  easily
• Scaled-response Utilizes a scale developed by
  the researcher to measure the attributes of some
  construct under study

3
Basic Question-Response FormatsOpen-Ended
Unprobed

• Unprobed format seeks no additional information
• What do you think about the services provided by
  Olive Garden?
• Advantage
• Allows respondent to use his or her own words
• Disadvantages
• Difficult to code and interpret
• Respondents may not give complete answers

4
Basic Question-Response FormatsOpen-Ended Probed

• Probed format includes a response probe
  instructing the interviewer to ask for additional
  information
• Do you have any other thoughts about Olive
  Garden?
• Advantage
• Elicits complete answers
• Disadvantage
• Difficult to code and interpret

5
Basic Question-Response FormatsClose-Ended
Dichotomous

• Dichotomous has only two response options, such
  as yes or no
• Do you agree or disagree with the statement
  Olive Garden is better than Carinos?
• Advantage
• Simple to administer and code
• Disadvantages
• May oversimplify response options
• Assumes researcher knows options

6
Basic Question-Response FormatsClose-Ended
Multiple Category

• Multiple response has more than two options for
  the response
• E.g., If you were to buy a TV tomorrow, which
  brand would you buy?
• (a) Sony (b) Toshiba (c) RCA (d) Panasonic (e)
  Other
• Advantages
• Allows for broad range of possible responses
• Simple to administer and code
• Disadvantages
• Must distinguish pick one from pick all that
  apply
• May alert respondents to response options of
  which they were unaware

7
Basic Question-Response FormatsScaled-Response
Unlabeled

• Unlabeled uses a scale that may be purely
  numerical or only the endpoints of the scale are
  identified
• E.g., On a scale of 1 to 7, how would you rate
  Sony TVs on picture quality?
• Advantages
• Allows for degree of intensity/feelings to be
  expressed
• Simple to administer and code
• Disadvantage
• Respondents may not relate well to the scale

8
Basic Question-Response FormatsScaled-ResponseLa
beled

• Labeled uses a scale in which all of the scale
  positions are identified with some description
• Sony TVs are better than Panasonic TVs
• _S.Disagree _Disagree _Neutral _Agree _ S.Agree
• Advantages
• Allows for degree of intensity/feelings to be
  expressed
• Simple to administer and code
• Respondents can relate to scale
• Disadvantage
• Scale may be forced or overly detailed

9
Considerations in Choosing a Question-Response
Format

• The nature of the property being measured
• Genderdichotomous liking for chocolatescale
• Previous research studies
• Use format in previous study if desire to compare
• The data collection mode
• Cannot use some scales on the phone
• The ability of the respondent
• Kids cant relate to scaled response
• The scale level desired

10
Basic Concepts in Measurement

• Measurement determining how much of a property
  is possessed by an object
• Properties specific features or characteristics
  of an object that can be used to distinguish it
  from another object
• Objective properties are physically verifiable
• Subjective properties are mental constructs

11
Scale Characteristics Determine the Level of
Measurement

• Description The use of a descriptor, or label,
  to stand for each unit on the scale yes
  no, male female,etc. ALL levels of
  measurement have description.
• Order The relative sizes of the descriptors are
  known allowing us to say one is
  greater/less-than the other. Not all scales
  have order

12
Scale Characteristics Determine the Level of
Measurement

• Distance The differences between the descriptors
  are known there is a 1 difference between 4
  and 5. There is a 10 degree difference between
  90 and 100 degrees.
• Origin There is a true, natural zero There is
  a zero level of dollars, market share, sales.

13
Levels of Measurement

• Nominal scales those that have just description
• E.g., Brand last purchased, Gender
• Order?
• male female?
• Honda
• Distance? Origin?
• male - female 1
• Ordinal scales Possess description and order
  The researcher can rank-order the respondents or
  responses
• E.g., Would you say the prices in Wal-Mart are
  ___Higher than Sears ___About the same ___Lower
• Distance? Origin?

14
Levels of Measurement

• Interval scales those in which the distance
  between each descriptor is equal Possess
  description, order, and distance
• E.g., Please indicate your level of agreement I
  always look for bargains 1 2 3 4 5 (1
  strongly disagree 5 strongly agree)
• Description? Order? Distance? Origin?
• Ratio scales Possess all four characteristics
  Ones in which a true zero exists
• E.g., What is the probability that you will pass
  Exam 2? ____ percent
• Description? Order? Distance? Origin?

15
Broad Types

• Comparative
• Noncomparative

16
Figure 9.6 Paired Comparison Scaling
Figure 9.6 Paired Comparison Scaling
Instructions We are going to present you with ten
pairs of shampoo brands. For each pair,
please indicate which one of the two brands of
shampoo in the pair you would prefer for personal
use. Recording Form
Jhirmack
Finesse
Vidal Sassoon
Head Shoulders
Pert
Jhirmack
0
0
1
0
Finesse
0
1
1A
0
Vidal Sassoon
1
1
1
0
Head Shoulders
0
0
0
0
Pert
1
0
1
1
Number of times preferred
2
3B
0
4
1
A A 1 in a particular box means that the brand in
that column was preferred over the brand in the
corresponding row. A 0 means that the row brand
was preferred over the column brand. B The
number of times a brand was preferred is obtained
by summing the 1s in each column.

17
Figure 9.7 Rank Order Scaling
Figure 9.7 Rank Order Scaling
Instructions Rank the various brands of
toothpaste in order of preference. Begin by
picking out the one brand that you like most
and assign it a number 1. Then find the second
most preferred- brand and assign it a number 2.
Continue this procedure until you have ranked all
the brands of toothpaste in order of preference.
The least preferred brand should be assigned a a
rank of 10. No two brands should receive the
same rank number. The criterion of preference
is entirely up to you. There is no right or wrong
answer. Just try to be consistent. Brand
Rank Order 1. Crest
2. Colgate 3. Aim 4. Mentadent 5. Macleans
6. Ultra Brite 7. Close Up 8. Pepsodent 9.
Plus White 10. Stripe
18
Figure 9.8 Constant Sum Scaling
Figure 9.8 Constant Sum Scaling
Instructions Below are eight attributes of
bathing soaps. Please allocate 100 points among
the attrib- utes 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. Form AVERAGE RESPONSES OF
THREE SEGMENTS Attribute
Segment I Segment II
Segment III 1. Mildness
8
2 4 2.
Lather 2
4
17 3. Shrinkage 3
9
7 4. Price
53 17
9 5.
Fragrance 9
0 19
6. Packaging 7
5
9 7. Moisturizing
5 3
20 8. Cleaning Power
13 60
15 Sum
100
100 100
19
Figure 10. 3 A Classification of Non Comparative
Rating Scales
Figure 10.3 A Classification of Noncomparative
Rating Scales
Noncomparative Rating Scales
Continuous Rating Scales
Itemized Rating Scales
Semantic Differential
Stapel
Likert
20
Workhorse Scales Used in Marketing Research

• The Modified Likert Scale
• The Stapel Scale
• The Semantic Differential Scale
• Halo effect

21
Figure 10.4 Balanced and Unbalanced Scales
Figure 10.4 Balanced and Unbalanced Scales
Balanced Scale
Unbalanced Scale
Surfing the Internet is ____ Extremely Good ____
Very Good ____ Good ____ Bad ____ Very Bad ____
Extremely Bad
Surfing the Internet is ____ Extremely Good ____
Very Good ____ Good ____ Somewhat Good ____
Bad ____ Very Bad
22
Figure 10.5 Rating Scale Configuration
Figure 10.5 Rating Scale Configurations
A variety of scale configurations may be employed
to measure the comfort of Nike shoes. Some
examples include Nike shoes are 1) Place an X
on one of the blank spaces Very

Very
Uncomfortable

Comfortable 2)Circle the number Very
1 2 3 4 5 6
7 Very Uncomfortable

Comfortable 3)Place
an X on one of the blank spaces Very
Uncomfortable Neither Uncomfortable nor
Comfortable Comfortable
23
Figure 10.5 Rating Scale Configuration Continued
Figure 10.5 Rating Scale Configurations
(continued)
24
Reliability of Scales

• Reliability
• consistency of responses to identical or near
  identical questions
• reliable measures obtain identical or very
  similar responses from the same person

25
Reliable?
26
Reliable?
27
Reliability of Scales

• Testing for reliability
• Test-Retest Reliability
• administer scale at two different points in time
• compare to see if the responses are consistent

28
Reliability of Scales

• Improving Reliability
• Revising questions
• pretests
• Throw-out Respondent(s)
• carelessness
• outliers

29
Validity of Scales

• Validity
• The accuracy of the measurement
• Does it measure what it is supposed to measure?

30
Valid and Reliable?
31
Valid and Reliable?
32
Valid and Reliable?
33
Validity of Scales

• Content (Face) Validity
• Does the question look like it measures what it
  is supposed to?
• Criterion Validity
• Does the measure relate to other measures as we
  would expect?

34
Validity of Scales

• Convergent Validity
• Do two methods of collecting the data agree?
• Discriminant Validity
• Does the measurement of different constructs
  differ?