We were disappointed by the article by Morello et al1 that was recently published in the ARCHIVES. It is our opinion that their discussion was misleading and their conclusions were iniquitous.
A total of 19 evaluable patients is not a sufficient number to arrive at any statistically significant conclusions in a double-blind study, especially with ordinal data. The authors admit that "260 patients per paired crossover study would be necessary to provide 80% power to detect a mean difference between treatments of approximately one third of the difference between mild and moderate pain at a .05 significance level." Nevertheless, the authors conclude that "mean pain diary and global pain relief score data indicate no statistical difference" between gabapentin and amitriptyline therapy in relieving pain.
Fudin J, Audette CM. Gabapentin vs Amitriptyline for the Treatment of Peripheral Neuropathy. Arch Intern Med. 2000;160(7):1040-1041. doi: