Skip to content
Prev 396611 / 398502 Next

OFF TOPIC: Nature article on File Drawer Problem in Reserach

I know you didn't want to stimulate discussion, but the problem is not
confined to publication.  "Adverse reaction to medication" monitoring
programs are plagued by a similarly massive under-reporting problem:
adverse reactions are seldom reported unless they are particularly bad
or surprising.  (The Ministry of Health in my country estimates 90% of
cases are never reported.)  Remembering to check for possible bias
from unreported cases is a human problem for analysts.  Which, if any,
R packages have proven useful to detecting the existence of a
systematic under-reporting problem might well be an appropriate topic
for this list.
On Thu, 25 Jul 2024 at 02:44, Bert Gunter <bgunter.4567 at gmail.com> wrote: