In Reply: The scale used in our study, to which
Drs Schiebel and Ebbert refer, was not a true Likert scale as it did not have
a pain description associated with each number. Only the extreme ends of the
scale had word descriptions (0=no pain, 10=worst possible pain) so our scale
could be more accurately characterized as a numerical rating scale. Numerical
rating scale scores can be analyzed using parametric methods.1
Furthermore, we did not analyze single numerical rating scale scores, but
rather the mean of daily scores recorded over a week for each patient. The
treatment group mean was an average of the means per patient. Since the central
limit theorem2 holds that means tend to
be normally distributed, it was appropriate to use parametric analyses.
Backonja M. Gabapentin for Painful Diabetic Neuropathy—Reply. JAMA. 1999;282(2):133–134. doi:10-1001/pubs.JAMA-ISSN-0098-7484-282-2-jbk0714
Coronavirus Resource Center
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: