Rapid responses are electronic comments to the editor. They enable our users
to debate issues raised in articles published on bmj.com. A rapid response
is first posted online. If you need the URL (web address) of an individual
response, simply click on the response headline and copy the URL from the
browser window. A proportion of responses will, after editing, be published
online and in the print journal as letters, which are indexed in PubMed.
Rapid responses are not indexed in PubMed and they are not journal articles.
The BMJ reserves the right to remove responses which are being
wilfully misrepresented as published articles or when it is brought to our
attention that a response spreads misinformation.
From March 2022, the word limit for rapid responses will be 600 words not
including references and author details. We will no longer post responses
that exceed this limit.
The word limit for letters selected from posted responses remains 300 words.
Prior to my current position, I worked part-time as a
biostatistician at Royal Melbourne Hospital, serving also
Western Hospital. These are two large tertiary hospitals,
active in research, yet neither currently employs
a statistician. As I still serve on the research ethics
committee for these hospitals many of the cries for statistical help still
come my way.
So it was not surprising to receive a call this morning
from a surgical registrar undertaking an RCT. His question
was "what statistical test should I use". However he did
not have a clearly defined hypothesis: under pressure
he said he "would look at a number of outcomes".
This is of course methodological nonsense. Hypothesis testing
only makes sense with a pre-existing hypothesis. Otherwise,
one could compare 20 different outcomes and report whichever
gave the lowest p-value.
So while encouraging the conduct of RCT's is a fine thing,
it might be counter-productive in the absence of appropriate
training and support. The medical profession is still slow
to accept that medical training is not sufficient for all
research tasks and that outside expertise should be sort
BEFORE undertaking research. Of course those who run large
trials have realised this long ago and no pharmaceutical
company would think of submitting a trial proposal without
the input of a biostatistician. It must be accepted that
the call for more evidence-based medicine requires not
just more research, but better research, and that this
entails better resources.
Staff need training before undertaking RCT's
Prior to my current position, I worked part-time as a
biostatistician at Royal Melbourne Hospital, serving also
Western Hospital. These are two large tertiary hospitals,
active in research, yet neither currently employs
a statistician. As I still serve on the research ethics
committee for these hospitals many of the cries for statistical help still
come my way.
So it was not surprising to receive a call this morning
from a surgical registrar undertaking an RCT. His question
was "what statistical test should I use". However he did
not have a clearly defined hypothesis: under pressure
he said he "would look at a number of outcomes".
This is of course methodological nonsense. Hypothesis testing
only makes sense with a pre-existing hypothesis. Otherwise,
one could compare 20 different outcomes and report whichever
gave the lowest p-value.
So while encouraging the conduct of RCT's is a fine thing,
it might be counter-productive in the absence of appropriate
training and support. The medical profession is still slow
to accept that medical training is not sufficient for all
research tasks and that outside expertise should be sort
BEFORE undertaking research. Of course those who run large
trials have realised this long ago and no pharmaceutical
company would think of submitting a trial proposal without
the input of a biostatistician. It must be accepted that
the call for more evidence-based medicine requires not
just more research, but better research, and that this
entails better resources.
Yours sincerely,
Graham Byrnes PhD
Competing interests: No competing interests