Letters Section Editor: Robert M. Golub,
MD, Senior Editor.
In Reply: I strongly agree with Drs Hauben
and van Puijenbroek that true signals should emerge from clinical judgment
and that statistical algorithms, such as PRRs,1- 5 should
be used as supplements to clinical and epidemiological judgment, not replacements.
I also agree that the value of statistical algorithms even in that role remains
unproven. Unfortunately, however, statistical algorithms are too often used
alone, in publications and in the courtroom, as if they represent analyses
useful for hypothesis testing, which is inappropriate.
Strom BL. Evaluation of Suspected Adverse Drug Reactions—Reply. JAMA. 2005;293(11):1324-1325. doi:10.1001/jama.293.11.1324-b