Page 184 - DMGT209_QUANTITATIVE_TECHNIQUES_II

Unit 9: Attitude Measurement and Scaling Techniques

The disadvantage of this method is that, if the interval between first and second test is more the Notes
scale will be less reliable.
Second disadvantage is, it is difficult to convince the original respondents to take the test for
second time.
Third disadvantage is that, the second time answer may be influenced by the first time answer.
Assume that, an opinion about the hospital service is asked. Two weeks later, if the same
question is asked, the reply by respondent will be influenced by what was told the first time.

Equivalent Forms Reliability

In this method 2 “equivalent” scales are used to obtain consistent results. So, the researcher
administer one scale to the respondent and 2 weeks later another scale, which is equivalent of
the first one to the same respondent.
The greatest problem of this method is to construct 2 scales that appear to be different but have
similar effect. This alternative forms test is similar to the test-retest method, except that the test-
retest method uses the same measuring instrument both the times.

Internal Consistency

In this method two or more measurement of the same concept is taken at the same time and then
compares to see if they agree with each other. Suppose we use Likert scale and offer choices from
strongly agree to strongly disagree to determine consumer attitude towards the service rendered
by Big Bazar. Suppose the researcher prepares 4 statements scale to measure this:
1. I enjoy shopping at Big Bazar.
2. All my needs for my household are satisfied by shopping in Big Bazar.
3. Service provided to me by Big Bazar is excellent.
4. I like the front line salesman regarding the service rendered.
The degree to which the 4 statements show correlation across a sample of respondents indicates
the reliability of the measure. If correlation is high, then reliability will also be high.
Methods to Improve Reliability
i. Number of measurements is to be increased. Instead of conducting one test, average
scores of several equivalent forms of the test is to be considered for reliability.
ii. Controls used for conducting the experiment must be good. Example, (a) measuring device
must be accurate. (b) The researcher who administers must be trained to avoid bias in
respondents.
iii. Items to be measured must be stated clearly.

Validity

The paradigm of validity focused in the question “Are we measuring, what we think, we are
measuring”? Success of the scale lies in measuring “What is intended to be measured?” Of the
two attributes of scaling, validity is the most important.

There are several methods to check the validity of the scale used for measurement.
1. Construct Validity: A sales manager believes that there is a clear relation between job
satisfaction for a person and the degree to which a person is an extrovert and the work
performance of his sales force. Therefore, those who enjoy high job satisfaction, and have

LOVELY PROFESSIONAL UNIVERSITY 179