Here are some resources about likert scales:
In 1999 an interesting sequence of discussions regarding the use of
the Likert scale appeared on the AERA Division D LIST SERV. Consider a
scale such as: Agree Tend to agree Undecided Tend to disagree Disagree
Dr. Dennis Roberts of Penn State, on August 30 1999, regarding the
existence of the middle option, made the following statements
regarding use of this scale: “There is no assurance whatsoever that a
subject choosing the middle scale position harbors a neutral position.
A subject’s choice of the scale midpoint may result from ignorance,
uncooperativeness, reading difficult, reluctance to answer, or
inapplicability (Note that Dr. Roberts included definitions in his
email for each of these possible interpretations). “In all the cases
above, the investigator’s best hope is that the subject will not
respond at all (?). Unfortunately, the seemingly innocuous middle
point counts, and, when a number of subjects choose it for invalid
reasons, the average response level is raised or lowered erroneously
(unless, of course, the mean of the valid responses is exactly at the
scale midpoint).
[...]
Think twice before using summed or scaled Likert scores, especially if there is more than
a single construct in the instrument. Consider using percentages of individual ordinal
categories or, if the sample size is small, collapsing categories and using percentages.
AN EMPIRICAL EXAMINATION OF THE LIKERT SCALE: SOME ASSUMPTIONS, DEVELOPMENT, AND CAUTIONS, Chester H. McCall
"One of the issue about analyzing data from likert scale is assuming that you can use things like means.
Likert scales fall within the ordinal level of measurement.2–4 That is, the response categories have a rank order, but the intervals
between values cannot be presumed equal, although, as Blaikie3 points
out, ...researchers frequently assume that they are. However, Cohen
et al.1 contend that it is illegitimate to infer that the intensity
of feeling between strongly disagree and disagree is equivalent to
the intensity of feeling between other consecutive categories on the
Likert scale. The legitimacy of assuming an interval scale for
Likerttype categories is an important issue, because the appropriate
descriptive and inferential statistics differ for ordinal and interval
variables 1,5 and if the wrong statistical technique is used, the
researcher increases the chance of coming to the wrong conclusion
about the significance."
Likert scales: how to (ab)use them, Susan Jamieson
