TYPE AND USES OF ATTITUDE SCALES
Attitude
scales are usually used for the measurement of attitude towards any other
individuals, objects, ideas or things. These explain what the individual‟s
acquired ways of thinking are for the present construct and that is attitude.
Thus attitude scales (also known as opinionnaries) which usually consist of a
large number of statements towards objects of attitude, are one such indirect measure.
A measurement instrument that contains some combined statements related with
particular attitude or its sub-dimensions and provides a combine score is
called an attitude scale. Anastasi (1976) defined that attitude scales are
designed to provide a quantitative measure of the individual's relative
position along a uni-dimensional attitude continuum and it yields a total score
indicating the direction and intensity of theindividual‟s attitude towards an
object or other stimulus category. Thus, one method of assessing the attitudes
of an individual concerning a particular concept or object is, by using an
attitude scale. Since an attitude scale is a hypothetical or latent variable
relatively an immediately observable variable, attitude measurement consists of
the assessment of an individual's responses to a set of situations. The set of
situations is usually a set of statements (items) about the attitude object, to
which the individual responds with a set of specified response categories
"agree" and disagree".
Types attitude scales
·
Arbitrary Scales
·
Differential Scales
·
Summatted Scales
·
Cumulative Scales
·
Factor Scales
Arbitrary Scale
Arbitrary
Scales are developed on adhoc basis and designed largely through the
researcher„s own subjective selection of items. The researcher first collects a
few statements or items which he believes are unambiguous and appropriate to a
given topic. Some of these are selected for inclusion in the measuring
instrument and then people are asked to check in a list the statements with
which they agree. The chief merit of such scales is that they can be developed
very easily, quickly and with relatively less expense. They can also be
designed to be highly specific and adequate. Because of these benefits, such
scales are widely used in practice. At the same time, there are some
limitations of these scales. The most important one is that the researcher does
not have objective evidence that such scales measure the concepts for which
they have been developed. Others have simply to rely on researcher‟s insight
and competence.
Differential Scales
Differential
scales are associated with the name of L.L. Thurstone. These have been
developed using consensus scale approach. Under such approach the selection of
items is made by a panel of judges who evaluate the items keeping in view of
whether they are relevant to the topic area and unambiguous in implication
(Kothari, 2008).There are conditions, when the method of paired comparison is
not well suited to the situation, the reason being that number of statements to
be scaled is large probably because subjects do not have the patience to make a
large number of comparative judgments. In such a situation, the solution is to
scale the statements through the method of equal appearing interval where each subject
is required to make only one comparative choice for each statement. Along with
the statements, each subject is given 11 cards on which A to K are written.
These cards are arrangedbefore the subjects in a manner that A is kept at the
extreme left. „A‟ indicates the most unfavourable interval and „K‟ is kept
extreme right and it represents the most favourable interval. The middle
category is designated by the letters G to K which represent various degrees of
favourableness and the cards lettered from E to A represent various degrees of
unfavourableness. A number of statements, usually 20 or more, are gathered that
express various points of views towards the situation (Best, 2006). | A | B | C
| D | E | F | G | H | I | J | K | Unfavourable Neutral FavourableThurstone and
Chave defined only the two extremes and the middle category (of the 11 intervals)
on the ground that the undefined between successive cards would represent equal
appearing intervals for all the subjects. The subjects are requested to sort
the given statements in terms of 11 intervals represented by 11 cards.
Ordinarily, there is no limit for sorting. But Thurstone and Chave reported
that subjects took 45 minutes in sorting 130 statements into 11 intervals. Thurstone
and Chave made the following assumptions in this method:
(i)
The intervals into which the statements are sorted or rated are equal.
(ii)
The attitude of the subjects does not influence the sorting of the statements
into the various
In
the other words, subjects having favourable attitudes and those having
unfavorable attitude would do the sorting in a similar manner. Thus the scale
values of the statement are independent of the attitude of the judges
(Chanderakandan, et al. (2001).
Summated Scales or Likert Scales
A Summated scale or Likert scale is a
psychometric scale commonly involved in research that employs questionnaires.
It is the most widely used approach to scaling responses in survey research,
such that the term (or more accurately the Likert-type scale) is often used
interchangeably with rating scale, although there are other types of rating
scalesThe scale is named after its inventor, psychologist Rensis Likert.A scale
can be created as the simple sum or average of questionnaire responses over the
set of individual items (questions). In so doing, Likert scaling assumes
distances between each choice (answer option) are equal. Many researchers
employ a set of such items that are highly correlated (that show high internal
consistency) but also that together will capture the full domain under study
(which requires less-than perfect correlations).
Cumulative Scales
The
method of cumulative scaling is developed by using Guttman‟s scale. Guttman‟s
method of scale analysis or scalogram analysis differs considerably from the
two methods of attitude scales construction discussed previously. The Guttman
Scale is based upon the methods of cumulative scaling and has been defined by
Guttman (1950) himself as -“We shall call a set of items of common content a
scale if a person with a higher rank than another person is just high as orhigher
on every item than the other person”It states that a scale will mean a set of
items of common content subject to the condition that a person with higher rank
or score will rank higher than another person on the same set of statements. It
is in such condition that Guttman‟s Scale operates. For example, a person whoresponds
with “yes” to item (a) will also be responding in “yes” term to items (b), (c)
and (d). All the four items are measuring the same dimension, that is, height
and Guttman (1945) called it uni-dimensional scale”. Similarly, if a set of
attitude statements measure the same attitude, they are said to constitute a
uni-dimensional scale or a Guttman Scale. According to Guttman, one advantage
of the uni-dimensional scale is that from the total score of the person one can
reproduce the pattern of his responses to the statements. Suppose, for example,
that in the above sample, “yes” is given a weight of 1 and “no” is given a
weight of 4, we can say that he has responded “yes” to items a,b,c &d.
Likewise, if a person has secured a total weight of 3, he has responded “yes”
to item b, c and d “No” to item a. Such prediction regarding the perfect
reproducibility is true in a perfect Guttman scale only. In case of attitude, statements
showing perfect reproducibility are rarely achieved because some degrees of irrelevancy
is always present.A case of perfect reproducibility has been demonstrated where
in responses of 10 subjects towards five items have been displayed. Each item
has two responses categories –Agree and Disagree. The response category “Agree”
is scored with one the other response category “Disagree” is scored with 0.
Subsequently, an attempt is made to evaluate the scalability of the items. If
the coefficient of reproducibility is below 0.90, no enumerative scale is said
to exist between the values 0.85 to 0.90, a quasi-scale is said to exist. Thus
for Guttman, the co-efficient of reproducibility must be at least 0.90 for
constituting the cumulative scale.The major criticism of the Guttman scale is
that it ignores the problem of selecting representative items from the initial
pool. As a matter of fact, no scientific procedures have been instituted for selection
of items.
Factor Scales
Factor
scales are developed through factor analysis or on the basis of
inter-correlation of items which indicates that a common factor accounts for
the relationships between items. Kothari (2008) cited Emory, (1976) that factor
scales are particularly “useful in uncovering latent attitude dimensions and
approach scaling through the concept of multiple-dimension attribute space. More
specifically the two problems viz., how to uncover underlying (latent)
dimensions which have not been identified, are dealt with through factor
scales. An important factor scale based onthe factor analysis is Semantic
Differential (S.D.) and the other one is Multidimensional Scaling.
(i) Semantic differential scale:-
Semantic differential scale or the S.D. scale developed by Charles E. Osgood,
G.J. Suci and P.H. Tanenbaum (1957), is an attempt to measure the psychological
meanings of an object to an individual. This scale is based on the presumption
that an object can have different dimensions: - property space or what can be
called the semantic space- in the context of Semantic differential scale. The
semantic differential technique is meant for obtaining a person‟s psychological
reactions to certain objects, persons or ideas under study. The term semantic
differential means a study of the differences in the psychological meanings of an
object etc. It consists of a number of bipolar adjectives each having seven
equally spaced scale points. The respondent indicates an attitude or opinion by
checking on any one of seven spaces between the two extremes.
(ii)Multidimensional scaling: Two approaches, the metric and the
non-metric both, are usually discussed and used in the context of MDS,
while attempting to construct a space containing mpoint such that m(m-1)/2
inter-point distance reflect the input data. The metric approach to MDS treats
the input data an interval scale data and solves by applying statistical
methods for the additive constant which minimizes the dimensionality of the
solution space. This approach utilizes all the dimensionality of the solution.
The non-metric approach first gathers the nonmetric similarities by asking
respondents to rank order all possible pairs that can be obtained from a set of
objects. Such non-metric data is then transformed into some arbitrary metric
space. and then the solution is obtained by reducing the dimensionality.
Uses of Arbitrary scales :
Arbitrary
scales are developed on ad hoc basis and are designed largely through the
researcher’s own subjective selection of items. The researcher first collects
few statements or items which he believes are unambiguous and appropriate to a
given topic. Some of these are selected for inclusion in the measuring
instrument and then people are asked to check in a list the statements with
which they agree.
The
chief merit of such scales is that they can be developed very easily, quickly
and with relatively less expense. They can also be designed to be highly
specific and adequate. Because of these benefits, such scales are widely used
in practice.
Uses of Differential scales
The
semantic differential is today one of the most widely used scales used in the
measurement of attitudes. One of the reasons is the versatility of the items.
The bipolar adjective pairs can be used for a wide variety of subjects, and as
such the scale is called by some "the ever ready battery" of the
attitude researcher.A specific form of the SD, Projective Semantics method uses
only most common and neutral nouns that correspond to the 7 groups (factors) of
adjective-scales most consistently found in cross-cultural studies (Evaluation,
Potency, Activity as found by Osgood, and Reality, Organization, Complexity,
Limitation as found in other studies). In this method, seven groups of bipolar
adjective scales corresponded to seven types of nouns so the method was thought
to have the object-scale symmetry (OSS) between the scales and nouns for
evaluation using these scales. For example, the nouns corresponding to the
listed 7 factors would be: Beauty, Power, Motion, Life, Work, Chaos, Law.
Beauty was expected to be assessed unequivocally as “very good” on adjectives
of Evaluation-related scales, Life as “very real” on Reality-related scales,
etc. However, deviations in this symmetric and very basic matrix might show
underlying biases of two types: scales-related bias and objects-related bias.
This OSS design had meant to increase the sensitivity of the SD method to any
semantic biases in responses of people within the same culture and educational
background.
Uses of summatted scales
·
To measure the social attitude Likert scale is
used.
·
It uses only the definitely favourable and
unfavorable statement.
·
It consists series of statements to which the
respondents is to react.
·
Each response is given as numerical score and
the total score of a respondents is found out by summing up his different
scores for different purposes.
·
The Likert scale uses several degrees of
agreement or disagreement.
Uses of cumulative scales
Highly
hierarchical and structured in nature: Due to the hierarchical and structured
nature of this scale, it can be extremely productive in short surveys and
questionnaires. For example, to analyze social distance, employee hierarchy,
stages of evolution etc.
Implemented
to gain insights for multiple queries: Guttman scale includes multiple
statements for the respondents to answer which occupies a short space in an
online survey.
More
intuitive than other uni-dimensional scales: The way in which the answers are
represented in this scale makes Guttman scale extremely intuitive for users.
Produces
data in a ranked manner: The statements mentioned in this scale have their
degree of importance and values associated accordingly. Thus, the results of
this scale are in terms of ranks.
No comments:
Post a Comment