2. • Measurement and Scaling
• Commonly used scales in business research
• Reliability and Validity of scales.
3. Scales and Measurements
• A scale is a technique to measure some thing. Scaling is used in ordering a
series of items along sort of continuum. – they are methods of turning a
series of qualitative facts into a quantitative series
• Measurements are yardsticks – Measurement in research consists of
assigning numbers to empirical events in compliance with a set of rules –
• Hence, measurement is a three part process
• (1) Selecting observable empirical events
• (2) Developing a set of mapping rules i.e. a scheme for assigning numbers
• (3) Applying mapping rule to each observation of that event. Example of
studying people who attend a auto show
5. Nominal Scale
• It is simply a system of assigning number symbols
to events in order to label them.
• example: assigning numbers to football players in
order to identify them – just for convenience
• no quantitative value
• can not come out with a meaningful value
• We use Mode as the measure of Central
Tendency – e.g. classifying the residents of a city
according to religious preferences.
6. Ordinal Scale
• The lowest level of the ordered scale that is commonly used is the
ordinal scale
• This scale places events in order
• E.g. Rank orders represent ordinal scales – a student’s rank in his
graduation class involves the use of ordinal scale.
• These scales have no absolute values – all that we can say is that
one person is higher or lower in rank on the scale
• E.g. Ram’s rank is 10 and Mohan’s is 40 – what do you conclude?
• If a is greater than b and b is greater than c, then a is greater than c
• just mentions greater than or less than , without stating how much
greater or less
• the appropriate method of central tendency is median
7. Interval Scale
• It has the power of nominal and ordinal scale plus one
additional strength
• The concept of equality of intervals.
• E.g. the interval between 1 and 2 equals the difference
between 2 and 3.
• In this case the intervals are adjusted in terms of some rule
that has been established as a basis for making the units
equal.
• These scales can have an arbitrary zero – it lacks a true zero
• The Fahrenheit scale is an example of an interval scale
• Mean is the appropriate measure of central tendency
8. Ratio Scale
• It incorporates all the powers of previous
three Scales
• They have an absolute or true zero of
measurement
• E.g. measurement of physical dimensions like
height, weight, distance and area
• Geometric mean or harmonic mean are the
measures of central tendency
9. Sources of error in measurement
• Respondent
• Situation
• Measurer – behavior, style and looks of
investigator may encourage or discourage
certain replies from the respondent
• Instrument – e.g. use of complex words,
ambiguous meaning etc.
10. Characteristics of Sound Measurement
• Sound measurement must meet the following
tests.
• Validity
• Reliability
• Practicality
11. Test of Validity
• It refers to the extent to which a test
measures what we actually wish to measure.
• It can also be thought of as Utility.
• Validity is the extent to which differences
found with a measuring instrument reflect
true differences among those being tested.
12. Test of Reliability
• A measuring instrument is reliable if it
provides consistent results
• E.g. if a scale is consistently overweighs
objects by 5 kgs is a reliable scale but is not a
valid scale
• Reliability is concerned with estimates of
degree to which measurement is free of
random or unstable error.
13. Test of Practicality
• This can be judged in terms of :
• Economy
• Convenience
• Interpretability
14. Scaling
• It is defined as ‘ the procedure for the
assignment of numbers ( or symbols) to a
property of objects in order to impart some of
the characteristics of numbers to the properties
in question’.
• It describes the procedure of assigning numbers
to various degrees of opinion, attitudes and
other concepts – a scale is a continuum,
consisting of the highest point and the lowest
point
15. Important Scaling Techniques
• Rating Scales: It involves qualitative
description of a limited number of aspects of a
thing or of traits of a person.
• We judge properties of objects without
reference to other similar objects.
• These ratings are in the form of “like – dislike”,
“excellent-good-average-below average-poor”.
• In practice three to seven point scales are
generally used
16. Rating Scale cont..
• There are two types of Rating scale-
• (1) The Graphic Rating Scale : various points
are usually put along the line to form a
continuum and the rater indicates his rating.
• E.g. How do you like the product?
17. Cont..
2) The Itemized rating scale ( Numerical Scale) :
• It presents a series of statements from which a respondent
• Selects one as best reflecting his evaluation.
• E.g. suppose we want to enquire as to how well does a
worker get along with his fellow workers:
a. He is almost always involved in some friction with fellow
worker
b. He is often at odds with one or more of his fellow workers
c. He some times gets involved in friction
d. He frequently becomes involved in friction with others
e. He almost never gets involved in friction with fellow
workers
18. Attitude Scale
• Thurstone defined ‘Attitude’ as “the degree of positive or negative feeling
associated with some psychological object like symbol, phrase, slogan,
person, institution, ideal or ideas towards which people can differ in
varying degrees.”
• While measuring the attitudes of the people, we generally follow the
technique of preparing the opinionnaire ( attitude scale) in such a way
that the score of the individual responses assigns him a place on a scale.
• People may conceal their attitudes and express socially acceptable
opinions – They may not really know how they feel about a social issue –
People may be unaware of their attitude about an abstract situation until
confronted with real situation – even behavior itself is at times not a true
indication of attitude.
• E.g- Politicians kissing babies
• Is this behavior a true expression of affection towards infants?
No
• Hence there is no sure method of measuring attitude.
19. Cont..• With all these limitations, several attitude scales were developed, they
are :
1. Arbitrary scales:
• Are developed on ad hoc basis and are designed largely on
researcher’s own subjective selection of items – researcher himself first
collects few statements or items which he believes are unambiguous and
appropriate to a given topic – some of these instruments are selected for
inclusion in the measuring instrument.
• E.g. consider a company image study –
• How do you regard company’s reputation :
1. As a place to work : Bad -- -- -- Good
2. As a institution of social responsibility : Bad -- -- -- Good
• These scales are easy to develop and relatively less expensive
• Demerits are – no objective evidence and we have to rely on researcher’s
insight and competence
20. Thurstone Scale ( Differential scale )
• This has been developed using consensus scale approach – In this
approach the selection of items is made by a panel of judges who
evaluate the items in terms of whether they are relevant to the
topic of area.
• Detailed procedure :
• 1) The researcher gather a large number of statements, usually 20
or more ;
• 2) These statements are submitted to a panel of judges ( 50 to 300
judges ), requesting them to classify these statements into eleven
groups.
• Those statements which he/she considers most favorable to the
object are put in the first group; those considered next most in the
second group ……… those consider most unfavorable in the last
group.
21. Cont..
• It may be noted here that only the neutral and the two
extreme categories ( most favored and most unfavoured)
on which the statements are to be judged are defined. The
remaining eight are unlabelled to create the impression of
equal appearing intervals between the three labels.
• 3) The scale value of a statement is computed as the
median position to which it is assigned by the group of
judges.
• 4) A final selection is made taking items or statements that
are spread out evenly along the scale from one extreme
position to the other and for which there are more judges’
agreement.
22. Cont..
• 3) Summated Scales ( Likert Scale )
• This scale consists of a set of items ( statements) to which the
subject is asked to react. The respondents are asked to respond to each
item in terms of several degrees of agreement or disagreement and the
scores may be, for eg. strongly agree - 5 ; agree-4; undecided-3; disagree –
2; and strongly disagree – 1. Total score is obtained when all the weights
are summated
• 4)Semantic Differential (S D) Scale:
• This is developed by Charles E.Osgood and others in 1957. The word
Semantic means relating to meaning in language. SD scaling is an attempt
to measure the psychological meanings of an object. This scaling
technique is used rather easily in decisional survey research. Its main use
has been in connection with comparison of brand and company images,
determination of attitudinal characteristics of consumers and analysis of
the effectiveness of promotional activities.
23. Cont..
• “The S D scale is a technique for psychological measuring of things,
usually concepts or objects of people. It consists of a series or set of
descriptive adjectives or phrases which are polar opposite”. They
are generally classified into three categories
• 1.Evaluative : Good – Bad ; Beautiful – Ugly; Clean – Dirty;
• Fair-Unfair
• 2.Potency : Large – Small; Strong – Weak; Thick – Thin;
• Loud-Soft; Deep – Shallow.
• 3.Activity : Fast – Slow; Active – Passive; Sharp-Dull.
• The respondents are asked to describe the concept under
investigation according to the set of scales using the method of
rating. Thus, the technique enables an investigator to examine both
the context and intensity of people’s attitudes.