In data analysis, we often have only
one measurement of a variable. In employee records, for example, we
may only have one data entry for employee age, start date, etc. This
is fine when the data is a measurement of something very objective
and when there is little scope for measurement error.
Sometimes however we are measuring
something that is very subjective, or might have high scope for measurement
error. Psychometric measures, for example, when we are surveying people
about subjective mental constructs such as satisfaction, are far trickier.
In such cases, there is a greater risk of measurement error, since
people understand survey questions differently. For instance, asking
employees in a survey, “Are you satisfied with your job?”
might be construed as:
-
“Do you like your job,
that is, just the tasks that you do?”
-
“Are you satisfied with all
the job elements, that is, not just the tasks
but also the pay, working conditions, etc.?”
-
“Are you happy with the
whole company, including elements
like their corporate ethics?”
These differences in
interpretation or understanding make the answers less reliable. In
addition, a given single-item measure might be biased by other things,
such as an employee rushing to fill in the survey and not really thinking
hard about a question. Even more objective assessments such as performance
appraisals by supervisors are open to measurement error of various
kinds.
In cases where the interpretation
is in the control of the person organizing the measurements, it is
generally better to gather data on a construct using more than one
measurement. This is referred to as “
multi-item
assessment.” In our Chapter 1 Accu-Phi
example, two of the constructs measured (trust and satisfaction) are
measured with multiple questions all asking different aspects of the
construct. For example, we might have constructed a survey using the
questions seen in
Figure 4.4 Possible multi-item measures of trust and satisfaction for
each variable.
You will generally be
able to find multi-item scales on most business, psychological, sociological
and other constructs in academic journal articles, which you can often
fairly safety adopt and adapt to your uses. These will have been previously
validated through careful scientific methods. If you wish to use a
previously designed scale – and you probably should, if possible,
since these have been tested for validity – try to find scales
tested and adapted for your local context (geography, industry, and
the like). You often will.
There are two issues
you may wish to consider when designing or choosing multi-item scales:
-
Reverse-worded
items. Reverse-worded question items are those
that run in the opposite direction to the flow of logic used by the
majority of items in the list. For example, in
Figure 4.4 Possible multi-item measures of trust and satisfaction, there are
four items for satisfaction. The first three are items where a high
score indicates
high satisfaction.
However, the fourth is an item where a high score indicates
low satisfaction.
These are called “reverse-worded questions.” There are
two things to understand about reverse-worded items.
-
The perceived benefits of reverse-worded
items. Why would you use reverse questions in
the mix? It has traditionally been believed that they work to deter
respondents from answering the questions in the list in a less than
thoughtful manner, perhaps just answering all of the items in a generally
positive manner but without thinking hard about differences in the
answers.
-
The downside of reverse-worded items. Unfortunately,
the data from reverse-worded items tends to not mix well with the
data from the rest of the list, which jeopardizes the reliability
of the overall scale. I suggest trying to avoid their use for this
reason. However, if you use previously designed scales (especially
older ones), they will sometimes include reverse items.
-
The ordering of multi-item scales in a bigger
research instrument. The second question is whether
to keep the items from a multi-item scale together in a research instrument
(for instance, in a survey, whether to ask all the trust questions
together, one after the other, in a section of the survey). If at
all possible, I suggest not keeping the items together, but rather
interspersing them between other questions. This keeps respondents
from falling into a pattern.
Finally, having designed
your question and answer protocols for data collection, and having
captured the data, you now have to deal with various issues in the
raw data. I discuss these issues next.