STEPS IN THE CONSTRUCTION AND STANDARDIZATION OF ATTITUDE SCALE

Introduction

The term Scaling is applied to the attempts to measure the attitude objectively. Attitude is a resultant of number of external and internal factors. Depending upon the attitude to be measured, appropriate scales are designed. Scaling is a technique used for measuring qualitative responses of respondents such as those related to their feelings, perception, likes, dislikes, interests and preferences.Attitude scales provide a quantitative measurement of attitudes, opinions or values by summarising numerical scores given by researchers to people's responses to sets of statements exploring dimensions of an underlying theme.

Definition

According to Merriam Webster dictionary, Attitude scale as a measure of the

relative quantity of an attitude possessed by an individual as contrasted with a reference group.

Likert technique of attitude Scale 

For the assessment of attitudes, various methods such as observation, question lists, incomplete sentences and storytelling as well as various techniques such as choosing the wrong one and content analysis have been employed. However, the most prominent and widespread method for the assessment of attitude has been attitude scales. Several attitude scales are being used such as Bogardus social distance scale, Thurstone scale, Likert type 

attitude scale, Guttman scales, Osgood emotional meaning scale.There are four basic techniques used to develop attitude scale. They are Likert scale, Semantic scale, Guttmann scale and Thrustone scale. However, Likert scales are a non‐

comparative scaling technique and are uni-dimensional (only measure a single trait) in nature. 

Respondents are asked to indicate their level of agreement with a given statement by way of an ordinal scale. The Likert-type scale is the most widely used method of scale construction because of its relative ease of construction, its use of fewer statistical assumptions, and the 

fact that, in contrast to other scaling techniques, no judges are required.

Steps in construction of Likert Attitude Scale

1) Discussion

Informally discuss the issues with the people, extension workers, experts, NGOs and also 

consult secondary sources. For an example if an investigator wants to develop a scale on 

attitude of schizophrenic patients among schizophrenic patients among caregivers, discuss the topic within caregivers, staff nurses who is giving care to schizophrenic patients, experts in the field such as psychiatrist, psychologist, psychiatric nurse, psychiatric social workers 

and NGOs. 

2) Review

Review of related literature to the particular topic of interest. Refer journals, books, articles and net sources. Literature review helps in the process of item generation for the scale.

3) Writing statements

Based on the discussion and extensive review, collect a set of such statements on the issues. Make the items simple and straight forward so that respondents are able to fill out the scale quickly and easily.

 Writing positive and negative statements

Write acceptance or rejection statements, it should imply a different degree of favourableor unfavourable attitude towards the issue in which an investigator intended to assess. Statement or item could be positive or negative. Positive statements should be objective  statements which are acceptable by those having the attitude, and just as unacceptable by those having the attitude, and just as unacceptable to those not having it. 

For an example: “I frequently use library resources to go beyond the required reading”. 

Negative statements should be objective statements which are acceptable to those not having the attitude and just as unacceptable to those having it. 

For an example: “Homework assignments are designed to meet course requirements. It is impractical in time and energy to do more than is required

4) Create an item pool

Continue writing items, both positive and negative, until item pool at least twice the size 

the size of instrument intended.

For an example “If an investigator plan to have 20 items in final scale, then create an item pool of 40 items”.

5) Editing of items

After having collected as many relevant statements as possible, the next step is to go through each item carefully.

6) Rank

After editing, select the items and give rating to the items. Rank orders the items on clarity and potency. Choose an equal number. Five categories are fairly standard. Some scale constructors use seven categories and some prefers four or six response categories with no 

middle category. All of these seem to work satisfactory.

7) Scoring

The points given for each response depend on whether the statement is positive or negative. The person who strongly agrees with a positive statement gets maximum points. One who strongly disagrees with a positive statement gets the minimum points. For the purpose of scoring, assign the numerical value of 5 to strongly agree, 4 to agree, 3 to undecided, 2 to disagree and 1 to strongly disagree. In case of the item is negative, reverse 

the order of scoring. 5 to strongly disagree, 4 to disagree, 3 to undecided, 2 to agree and 1 to strongly agree.

8) Write instructions which clearly explain how to select response on the form. Write in simple and easily understandable language.

9) Formatting the scale

Randomly order the selected items. Use letters to indicate choices such as SD, D, U, A, SA.

10) Validity

Validity is the extent to which the measure provides an accurate representation of 

what one is trying to measure. Validity includes both systematic and variable error components. A systematic error, also known as bias, is one that occurs in a consistent manner each time something is measured. For an example “A biased question would produce an error in the same direction each time it is asked”. Such an error would be systematic error. A variable error is one that occurs randomly each time something is measured. 

For an example “A response that is less favorable than the true feeling because the respondent was in a bad mood (temporary characteristic) would not occur each time that individual’s attitude is measured”. In fact, an error in the opposite direction (overly favorable) would occur if the individual were in a good mood. This represents a variable 

error.

11) Reliability

The term reliability is used to refer to the degree of variable error in a measurement. Reliability is the extent to which a measurement is free of variable errors. This is reflected when repeated measures of the same stablecharacteristic in the same objects show limited 

variation .

12) Pre-testing

Pre-testing the questionnaire is an essential step before its completion. The purpose of the pre-test is to enhance its clarity and to ensure acceptance of the study by the participants and also to check question wording. Provides information on possible ethical problems 

overlooked previously. Helps determine if the research questions or hypotheses are 

appropriate. Helps determine if the levels of measurement are appropriate for the selected variables. Provide a check that the population is appropriately defined. Provide information on the feasibility and the appropriateness of the sampling method. Helps determine sample 

size by allowing estimation of variance from the pre-test sample. Provide additional training for interviewers, instrument administrators, experimenters, coders, and data editors. Helps determine the length of the questionnaire.

13) Administration of questionnaire

Administer the questionnaire after reliability, validity and pre-test. The development of attitude scale requires the above mentioned steps and each step require constant attention to mould to shape the tool to be useful for all the professionals.

References

Reed, L.E. (1998) Performing a literature review Frontiers in Education Conference, FIE '98. 

28th Annual 380 - 383 vol.1. 

Patten.L.M. (2000) Writing Items to Measure Attitudes, Questionnaire research: A practical 

guide, chapter 4, pyrczak publisher-2nd edition, 33-44.

DeMaio, T. J.(1984). Social desirability and survey measurement: A review. In C. F.Turner 

& E. Martin (Eds.), Surveying subjective phenomena (Vol. 2, pp. 257-281). New York: 

Russell Sage.

Sommer, B. Sommer (1997) R. A Practical Guide to Behavioral Research: tools and 

techniques. Oxford University Press.151- 167.

Ary D, JacobsLC, Razavieh A, Sorensen C, (2009) Introduction to research in education, part 

4, attitude scale, 8th edition p 209- 210.). 

Benson J, Hocevar,D (1985 )The Impact Of Item Phrasing On The Validity Of Attitude 

Scales For Elementary School Children .Journal of Educational Measurement Volume 22, 

Issue 3, pages 231–240 

Edwards, A. L. Kenney, K. C , (1946) A comparison of the Thurstone and Likert techniques 

of attitude scale construction. Journal of Applied psychology, Vol 30(1),72-83). 

Sarsted TM, Mooi E (2011) A Concise guide to market research: the process, data, and 

methods using IBM and SPSS statistics. Springer publication.. p 65-66)

. Nosek BA., Banaji & Greenweld AG., (2002). Harvesting implicit group attitudes & beliefs 

from demonstration website, group dynamics, 6, 101-115.