Scaling Scaling TechniquesTechniques

Scaling Scaling TechniquesTechniques

MEANING OF SCALING Scaling describes the procedure of assigning numbers

to various degrees of opinion, attitude and other concept.

This can be done in two ways:

1. Making a judgment about some characteristics of an individual & then placing him directly on a scale.

2. Constructing questionnaires in such a way that the score of individual’s responses assigns him a place on scale.

Scaling is applied to the procedure for attempting to determine quantitative measures of subjective abstract concept.

SCALING TECHNIQUES-

Scaling Techniques are used when concepts to be measured are –

Complex, Abstract, We do not possess the standardized

measurement tools.

IMPORTANT SCALING TECHNIQUES

Rating Scales The Graphic Rating Scale The Itemized Rating Scale (Numerical Scale)

Ranking Scales Method of Paired Comparisons Method of Rank Order

Rating ScalesUsed to judge an object in absolute terms against some specific criteria. Ratings may be in forms such as – “like- dislike” “above average, average, below average” “excellent- good- average- below average- poor”

There is no specific rule whether to use a two-points, three points scale or scale with still more points.

3 to 7 points scale are generally used for the simple reason that more points on a scale provide an opportunity for greater sensitivity of measurement.

TYPES OF RATING SCALES1. The Graphic Rating Scales:Under it the various points are usually put along the line to

form a continuum & rater indicates his rating by simply marking a mark(√) at the appropriate point on a line.

e.g. How do you like the Product A?

(Please check √ )

Like verymuch

Like SomeWhat

Neutral Dislike SomeWhat

Dislike Very Much

MERITS-• Easy & Simple• Commonly used in practice.

DEMERITS-• The respondents may check at almost any position along the line which fact may increase the difficulty of analysis.

•The meaning of terms like ”very much” and “some what” may depend upon respondent’s frame of reference..

2. The Itemized Rating Scale(Numerical Scale)

It contain a series of statements from which respondent selects one as best reflecting his evaluation.

E.g. Suppose we wish to inquire as to how well does a worker get along with his fellow workers? We may ask respondent to select one from:

1. He is almost always involved in some friction with a fellow worker.

2. He is often at odds with one or more of his fellow workers.

3. He sometimes gets involved in friction.4. He infrequently becomes involved in friction with others.3. He almost never gets involved in friction with fellow workers.

MERITS-i. Provide more information & meaning to the rater.ii. More Reliable.

DEMERITS-i. Difficult to develop.ii. The statements may not say exactly what the

respondent would like to express.

Ranking Scales(Comparative Scales)

Respondents directly compare two or more objects & make choices among them.

TYPES:1. Method Of Paired Comparison:

Respondent can express his attitude by making a choice between two objects.

When objects are more than two, the number of judgements (N) are given by formula:

N = n(n-1)/ 2

where n = number of objects to be judged.

2. Method Of Rank Order Respondents are asked to rank their choices. Moreover,

a complete ranking is not needed when respondents are asked to rank only their first choice.

MERIT: Easier & Faster Method

DEMERITS:i. Data obtained is ordinal & hence rank ordering is an

ordinal scale with all its limitations.

ii. Respondents may become careless in assigning ranks, when there are many items

Different Scales For Measuring Attitudes Of People:

1. Arbitrary Scales

2. Differential Scales (Thrustone- type Scales)

3. Summated Scales (Likert- type Scales)

4. Cumulative Scales (Louis Guttmann's Scales)

Arbitrary Scales Designed largely through the Researcher’s own

subjective selection of items. Researcher first collect few statements which he

believes is appropriate to a given topic & then people are asked to check in a list the statement with which they agree..

Merits- Easy & quickly developed. Less Expensive. Highly specific & adequate

Demerit- Rely on Researcher’s insight & competence.

Selection of items is made by a panel of judges who evaluate the items in terms of whether they are relevant to the topic area & unambiguous in implication.

Developed by Consensus approach

MERITS- Most appropriate & reliable in measuring a single attitude.

DEMERITS- Costly & require efforts to develop. Provide less information about the respondent’s

attitude in comparison to other scales.

Differential Scales (Thrustone-type Scales)

Summated Scales (Likert type Scales) Developed by utilizing the item analysis approach Consist of number of statements favourable or

unfavourable to which respondent is asked to react. Each response is given a numerical score, indicating its

favourableness or unfavourableness & scores are totalled to measure the respondent’s attitude.

E.g. respondent may respond in one of following ways:

StronglyAgree(1)

Agree (2)

Undecided (3)

Disagree (4)

StronglyDisagree(5)

Merits- Relatively easy to construct in comparison to Thrustone

scale as it can be performed without a panel of judges. More Reliable & provide more information and data. Takes much less time to construct & is used frequently.

Demerits- We can only examine whether respondents are more or

less favourable to a topic but we can not tell how much more or less.

Total score can be secured by variety of answer patterns.

Cumulative Scales ( Louis Guttman’s Scalogram Analysis)

It consist a cumulative series of statements to which a respondent expresses his agreement or disagreement.

Statements are related to one another in such a way that an individual, who replies favourably to say item No.3 , also replies favourably to items No. 2 & 1 and one who replies favourably to item No.4 also replies favourably to items No. 3,2 &1 and so on.

Response Pattern in Scalogram Analysis Item Number4 3 2 1

Respondent Score

X----

XX---

XXX--

XXXX-

43210

X = Agree- = Disagree

Merits- Researcher’s subjective judgement is not allowed to

creep in the development of scale since the scale is determined by replies of respondents.

Appropriately used for personal, telephone or mail surveys

Demerits- In practice perfect cumulative scales are very rarely

found. Hardly constitute a reliable basis for assessing attitude

of persons toward complex objects. Bit more difficult in comparison to other scaling methods.

REFERENCES- Research Methodology Methods & Techniques

C.R. Kothari Methodology And Techniques of Social

Research

Wilkinsin & Bhandarkar

Theory And Practice In Social Research

Hans Raj