GUTTMAN SCALE [ SCALOGRAM ]

GUTTMAN SCALE [ SCALOGRAM ]

Guttman scale is a critical alternative to Thurstone’s and Likert’s methods. Guttman’s and Bogardus methods of scaling are known as scalogramanalusis or cumulative sealing.

Guttman scales are ones in which the items constitute a unidimensional series such that a answer to a given item preducts the answers to all previous items in the series. (e.g in an arithmetic scale, correctly answering a subtraction item preducts a correct answer to a prior item on addition, but not necessarily a later item on multiplication).  That  is,a respondent who answers on item in a positive way must answer lens difficult items also in a positive way. All the higher items Are rejected of the following items can be arranged in a hierarchy, ie, incase these attitudes are scaled, then a woman who possess fifth item, will also possess the first four items.

1.     Face powder

2.     Face Cream

3.     Nail polish

4.     Lipstick

5.     Perfume

These five characteristics from an acceptable Guttman Scale. The one who possess the first characteristics, also possesses the subsequent four characteristics. If a respondent have and there does not fit into the response patterns, it is an error. The detailed procedure four constructing a Guttman  scale is under a. selecting statements: collects a large number of statements on various points of say the attitude towards denationalization of public sector concerns. Arrange these statements according to a hierarchy of favourable-unfavourable  atttitutde. From these select at least to statements.

b.                 Gathering data: administer these statements to a representative sample of the universe under study. Ask the respondent to express their agreement or disagreement with all the statements.

c.                  Calculating scrores: those who answer the given items positively will have higher scores their those who answer them negatively. For calculating the scores-give ‘1’ to those who agree with a statement. Give ‘0’ to those who disagree with it. Add up all the respondents. Remove all items with larger as well as smaller scores. Calculate the mode (average) for each item.

d.                 Examine reproducibility. Arrange the items as well as the individuals in order. See whether they fit together. Examine the structure of responses and select appropriate patterns  by closely observing and intuitively as sensing the pattern of the responses for each respondent. The latest structure  of data can be unfolded with scalogram Analysis. If a particular item doesnot fit in, this would be an error. An error indicates deviation from a perfect hierarchy. Calculate the coefficient of reproducibility (RP) as follows.

COEFFICIENT OF REPRODUCIBILITY

Douglas W. Coleman, University of  Toledo, writes: “The coefficient of reproducibility measures how well we can predict any given students responses from his/her position with in the table, it should be at least .90”

The coefficient of Reproducibility is ;

Errors

Cof  **    =      1-

Totalresponse

First, sort the items (the columns) by item score, and persons ( the rows) by person score, then display the responses as a table called a Scalogram. For a perfect Guttman Scale with no errors, the scalegram will  form a triangle of  ‘1’ s (1 indicating a correct answer to the item) with no interior 0’s and no exterior 1’s. A Guttman error is an interior ‘0’ or an exterior 1 in the Scalogram.

Callout items that detract from reproducibility and unidimensionality. These are either unreliable or invalid, or both. Change the items and suitably modify. The scale in such a way that it suits all type of respondents.

e. Arranging statements: Arrange the statements in such a way that those who express agreement with the earlier statements also do so for the later statements. List the items before and after each other in such a manner that the pattern comes out well. When necessary,

Reproducibility can be increased by changing one or more statements.

ADVANTAGES

-                      These are simple and less expensive

-                      Pseudo metries are avoided. –It is a joint scale. It ranks the items as well as the respondents.

-                      It guarantees unidinesionality

-                      Reseacher’s subjective judgement is not allowed to creep in the development of scale since the scale in determined by the replies of respondents.

-                      Scalogram analysis can appropriately be used for personal, telephone or mail sarveys.

DISADVANTAGES

-                      The main difficulty in using this scaling technique is that in practice perfect cumulative or unidimensional scales are very rarely found and we have only to use its approximation testing it through coefficient of reproducibility or examining it on the basis of some other criteria.

-                      This method is not a frequently used method for the simple reason that is development procedure is tedious and complex.

-                      These scales hardly constitute a reliable basis for assessing attitudes of persons towards complex objects for predicting the behavioural  responses of individuals towards such objects. So this analysis is a bit more difficult in comparison to other scaling methods.