Stephen J.LurieMD, PhD, Senior EditorIndividualAuthor
To the Editor: We wish to raise 2 statistical
issues regarding the trial reported by Dr Kroenke and colleagues,1 who found that fluoxetine, sertraline, and paroxetine
were equally efficacious in treating depression. The authors conclude that
" . . . results unequivocally demonstrate the lack of differences among 3
SSRIs across a broad range of outcomes." There are a number of things that
the authors must do before the reader can endorse the adverb "unequivocally."
First, it would be helpful if the authors could provide a measure of the variance
in the 3- and 9-month change scores for each outcome in Tables 2 and 3. This
is especially important because no P values are provided.
Second, in evaluating the significance of all but the primary outcome, the
authors reported only adjusted P values using the
Sidak method for multiple comparisons. Based on this multiplicity adjustment,
no significant treatment × month interactions were found. We request
that the authors report unadjusted (comparisonwise) P
values in Tables 2 and 3 since the Sidak correction for multiplicity may be
overly conservative if the outcome measures being evaluated are correlated
(as functional status measures are) and if the number of outcome measures
being corrected for is relatively large (in this case, n = 16 and n = 9 for
2 separate corrections).2-4
Culpepper L, Heeren T. Is One Selective Serotonin Reuptake Inhibitor Better Than Another? JAMA. 2002;287(15):1935–1938. doi:10.1001/jama.287.15.1935
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: