Measurements

and Scaling
(Scoring) and
Coding

Source:ESSENTIALS OF MARKETING RESEARCH

Hair/Wolfinbarger/Ortinau/Bush
 Understand the role of measurement
in research
 Explain the four basic levels of scales
 Describe scale development and its

importance gathering primary data

 Measurement is the process of assigning numbers or
labels to objects, persons, states, or events in
accordance with specific rules to represent quantities
or qualities of attributes.
 We do not measure specific objects, persons, etc., we
measure attributes or features perceptions, beliefs,
that define them.
 Ex., What defines the person XYZ? What is a student’s
level of education? How customer oriented is our
company?
 Overriding Goal: To provide a valid and reliable
description or enumeration of the person, objects,
issue, etc. Accuracy of Measurement by clarity
1. Define concepts to be measured
2. Define attributes of the concepts
3. Select scale of measurement (data type)
4. Generate Items/Questions
◦ Wording and Scores
◦ Response format
5. Layout and design questionnaire
6. Pretest and refine
 Concept or Construct
◦ A generalized idea about a class of objects,
attributes, occurrences, or processes
◦ Concrete – demographics, traffic patterns,
purchase quantity
◦ Abstract – loyalty, personality, satisfaction,
leadership
 Attribute
◦ A single characteristic or fundamental feature
of an object, person, situation, or issue
◦ Often measure multiple attributes
 Not Very
at all Often
• I feel emotionally drained from my work 7 • I feel I treat some people in an impersonal
point scale manner
• I feel used up at the end of the day
• I've become more callous toward people since I
took this job
• I feel fatigued when I get up in the morning • I worry that this job is hardening me
and have to face another day on the job • I don't really care what happens to some people I
• Working with people all day is a strain for encounter at work
me • I feel others at work blame me for some of their
• I feel burned-out from my work problems
• I feel frustrated by my job • I can easily understand how people I work with
• I feel I'm working too hard on my job feel about things
• Working with people directly puts too much • I deal very effectively with problems people bring
stress on me me at work
• I feel I'm making a difference in other people's
• I feel like I'm at the end of my rope
lives through my work
• I feel very energetic
• I can easily create a relaxed atmosphere with
people at work
• I feel exhilarated after working with people closely
on my job
• I have accomplished many worthwhile things in
this job (Reverse Code)
• In my work, I deal with emotional problems very
calmly(Reverse Code)
Nominal
NominalScales
Scales

Ordinal
OrdinalScales
Scales

Interval
IntervalScales
Scales

Ratio
RatioScales
Scales
 Nominal
Nominal scales
scales focus
focus on
on only
only requiring
requiring aa
respondent
respondent to
to provide
provide some
some type
type of
of
descriptor
descriptor as
as the
the raw
raw response
response

Example.
Please indicate your current martial status:
__Married __ Single __ Single, never married __ Widowed
 Do not know for sure what the distance between 1 and 2 is, or
what the distance between 2 and 3 is

Ordinal
Ordinal scales
scales allow
allow the
the respondent
respondent toto express
express “relative
“relative magnitude”
magnitude”
between
between the
the raw
raw responses
responses to to aa question
question

Example.
Which one statement best describes your opinion of an Intel PC processor?
__ Higher than AMD’s PC processor
__ About the same as AMD’s PC processor
__ Lower than AMD’s PC processor
Statistics which can be used with the ordinal scale are the median,
various percentiles such as the quartile, and the (Spearman) Rank Correlation
in addition to the frequency tables and cross tabulations
 Interval
Interval scales
scales demonstrate
demonstrate the
the absolute
absolute differences
differences
between
between each
each scale
scale point
point

Example.
How likely are you to recommend the Toshiba Notebook to a friend?
Definitely will not Definitely will
1234567
The difference between interval scale and ordinal scale variables is that the distance
between 1 and 2 is the same as the distance between 2 and 3, and 3 and 4 in an
interval scale. Zero is Arbitrary
 Ratio
Ratio scales
scales allow
allow for
for the
the identification
identification of
of absolute
absolute
differences
differences between
between each
each scale
scale point,
point, and
and absolute
absolute
comparisons
comparisons between
between raw raw responses
responses

Example 1.
Please circle the number of children under 18 years of age currently living in your
household.
0 1 2 3 4 5 6 7 (if more than 7, please specify ___.)
 Understanding of the questions –fitness of Scale
 Appropriateness of Descriptor
◦ Extent to which the scale point elements match the data being
sought. How many scale points. Remember more the scale points
more the discriminatory power
 Discriminatory power of scale descriptors
 Ability to distinguish between categories no overlap
 Balanced versus unbalanced scales (Negative-Positive responses
balanced to maintain objectivity and non-bias )
 Forced (No neutral) or non-forced/free choice scales (Include Neutral
Choice)
 Desired measure of central tendency and dispersion for analysis
 Central Tendency
 Dispersion

◦ Mode ◦ Frequency
◦ Median distribution
◦ Range
◦ Mean
◦ Standard deviations
 If a nominal scale is used, analysis of raw data can
only be done using modes and frequency
distributions
 If ordinal scales are used, analysis of raw data can
be done using medians and ranges (plus modes
and frequency distributions)
 If interval or ratio scales are used, analysis of raw
data can be done through the use of sample
means and estimated standard deviations as the
sample statistic (plus the above)
 Questions

 Items are basically questions

 Need to ensure that enough questions are asked to
generate information necessary to address research
problems.
 Likely will have a mix of question types and scales of
measurement
 Multi-item, Composite or Index Measures
◦ A measurement scale containing multiple questions
addressing same construct or attribute
 Continuous Response Scale
 Likert Scale(Interval)
 Likert-Type Scale
 Semantic Differential Scale
 Behavioral Intention Scale
  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. Two
versions of a continuous rating scale are
depicted in figure

When version B is used, the respondent's score is determined either by dividing the line into as many
categories as desired and assigning the respondent a score based on the category into which his/her
mark fall by measuring the distance, in millimetres or inches, from either end of the scale
 in some cases item responses may be summed to create a score for a group of items
Hence, Likert scales are often called summative scales.

Ex:very satisfied very dissatisfied

+2 +1 0 -1 -2

A likert scale is treated as quasi-interval scale

format that asks respondents to indicate the extent to which
they agree or disagree with a series of mental or behavioral belief
statements about a given object More Points More Sensitivity
 Many researchers do consider likert-scale data to possess
only ordinal qualities. However, leading research studies,
for example in the marketing area, obtain measures such
as means and standard deviations from likert-scale data.
Indeed leading textbooks also follow this approach. .
 A recent study discusses these issues, as well as
demonstrating that data obtained from 5-point, 7-point and
10-point likert scales are approximately comparable in
terms of mean score (once re-scaled) and various
measures of variation and data shape. The study reference
is Dawes, John "Do Data Characteristics Change According
to the Number of Scale Points Used ? An Experiment using
5-point, 7-point and 10-point Scales" International Journal of
Market Research, Vol 50 2008.
Likert Type Scale

Score 6 5 4 3 2 1
 With an itemised scale, respondents are provided with a
scale having numbers and/or brief descriptions associated
with each category and are asked to select one of the
limited number of categories, ordered in terms of scale
position, that best describes the product, brand, company
or product attribute being studied. Examples of the
itemised rating scale are

itemised rating scales can take a variety of innovative forms

 A semantic differential scale is
unique bipolar scale format
that captures a person’s attitudes
and/or feelings about a given object

Interval Scale Mean and median are used for comparison

7 6 5 4 3 2 1
 A behavioral intention scale is
a special type of rating scale designed
to capture the likelihood that people
will demonstrate some type of
predictable behavior intent
toward purchasing an object or service
in a future time frame
4 3 2 1
Scoring methods may differ by the type of
scaling used (discrete or continuous)
Often a final index that is created by
Summing/Averaging
 Do proper conversion to scores from scale
before data entry
 Also remember to reverse code opposite

constructs
◦ I feel fatigued when I get up in the morning and have
to face another day on the job
◦ In my work, I deal with emotional problems very
calmly(Reverse Code)
 It lets you make sense of and analyze your data.
 For qualitative studies, it can help you generate a
general theory.
 The type of statistical analysis you can use depends on
the type of data you collect, how you collect it, and how
it’s coded.
 “Coding facilitates the organization, retrieval, and
interpretation of data and leads to conclusions on the
basis of that interpretation.”1
 Open ended and Closed ended Questions
Questions which permit any answer from the respondent in his own
words are called open-ended questions. Questions which structure the
possible answers beforehand are known as closed-ended questions.

An example of an open-ended question is " What do you like about

Surf detergent?"____________________________________
The respondent can say whatever he wants to, in response to this
question.
On the other hand, a closed-ended question which elicits similar information could
be "What do you like about Surf detergent?"
•.Its cleaning power
•.Its Price
•.Its fragrance
•.That it dissolves easily
•.Its stain-removing ability
•.Any other, (please specify)____________________________________
Here, options "a" to "e" are pre-determined, but "f" provides for anything else the
respondent wants to add.
 Categories and Variables

Variables: Gender Age Do you like

ice cream?

Categories: Male Female 18-25 26-33 34-41 yes no

 What is Post Coded Question Free-Floating
(Qualitative Data/Unpredictable) responses/no past
reference )
 What is Pre-coded Question(Highly structured and
responses can be predicted)
 Is it possible/wise to do 100% Pre-coding
Consider the need for free floating responses on
Questions like
What measures will help in tackling the recession?
reasons for using open-ended questions is that insufficient/ lack of information may
prohibit preparing response categories in advance
Numeric Code for Categories
taken by variables

more accurate and efficient data entry

Precoding means assigning codebook codes to variables in a study and recording them
on the questionnaire. It
A Section of
NSSO
Morbidity
Schedule
 Handling
“Don’t Know” and Missing Responses
Question: Do you have a productive relationship
with your present salesperson?

Years of Purchasing Yes No Don’t Know

Less than 1 year 10% 40% 38%

1 – 3 years 30 30 32

4 years or more 60 30 30
100% 100% 100%
Total n = 650 n = 150 n = 200

When the number of “don’t know” (DK) responses is low, it is not a problem.
If there are several given, it may mean that the question was poorly designed, too
sensitive, or too challenging for the respondent.
The best way to deal with undesired DK answers is to design better questions at the
beginning. If DK response is legitimate, it should be kept as a separate reply category.
Missing Values are non-responses to the questions and they can be coded in
spss
 Missing Data in SPSS

Listwise Deletion
cases are deleted from the sample

Pairwise Deletion
Missing are estimated with cases that
had data for each variable or pair
of variables in the analysis.

Replacement
variety of techniques
 Scaling facilitates appropriate scoring and
analysis
 Coding enhances entry efficiency, Reduce

Errors and improves analyzability

 We move to Data Analysis
 But Before that we will have a look at

autorecode and recode tools of SPSS

 .. Slide JKP analysis