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.
Articles, such as Sedgwick's most recent critical appraisal and quiz,
Statistical Question: Sources of bias in randomised controlled trials II
[1], provide an important service because bias can seriously distort study
results, and education in critical appraisal of the medical literature is
widely needed.
We wish to address one point. Sedgwick states that, "Attrition bias
occurs if the rates at which participants leave the trial, or their
characteristics or reasons for leaving, differ between treatment arms." He
goes on to state about the CHOPPS study[2], which he has appraised, that,
"Given that the proportion of children lost to follow-up was the same in
each group, attrition bias was minimised in this trial."
We believe that caution may be due even when drop out rates between
groups are equivalent. In some cases, the characteristics of those in one
group who drop out may differ significantly from those in the other group.
In that case, the groups would no longer be equal, which could affect
outcomes.
A report of the characteristics of the participants remaining in
their groups would be useful for readers in the same way that tables of
baseline characteristics are useful. Such reporting can expose potential
imbalances in reported characteristics. It would also help with external
validity assessments by providing greater understanding of the population
upon whom the results are actually based.
However, even if the characteristics are reported, the resulting
information is limited. Regardless of any seeming similarity between
groups, an imbalance could still occur because potentially key
characteristics may not be measured and/or reported or even be measurable.
Therefore, in most instances, the attrition rate, regardless of its
distribution, is important to consider when identifying potential threats
to validity.
1. Sedgwick P. Statistical Question: Sources of bias in randomised
controlled trials II. BMJ 2010; 341:c7053
2. James J, Thomas P, Kerr D. Preventing childhood obesity: two year
follow-up results from the Christchurch obesity prevention programme in
schools (CHOPPS). BMJ2007;335:762-5.
Competing interests:
No competing interests
06 January 2011
Sheri A. Strite
Principal & Managing Partner
Michael E. Stuart, MD, Clinical Assistant Professor, University of Washington & President and Medical Director
Attrition Bias Caution: Non-differential Loss Between Groups Can Threaten Validity
Articles, such as Sedgwick's most recent critical appraisal and quiz,
Statistical Question: Sources of bias in randomised controlled trials II
[1], provide an important service because bias can seriously distort study
results, and education in critical appraisal of the medical literature is
widely needed.
We wish to address one point. Sedgwick states that, "Attrition bias
occurs if the rates at which participants leave the trial, or their
characteristics or reasons for leaving, differ between treatment arms." He
goes on to state about the CHOPPS study[2], which he has appraised, that,
"Given that the proportion of children lost to follow-up was the same in
each group, attrition bias was minimised in this trial."
We believe that caution may be due even when drop out rates between
groups are equivalent. In some cases, the characteristics of those in one
group who drop out may differ significantly from those in the other group.
In that case, the groups would no longer be equal, which could affect
outcomes.
A report of the characteristics of the participants remaining in
their groups would be useful for readers in the same way that tables of
baseline characteristics are useful. Such reporting can expose potential
imbalances in reported characteristics. It would also help with external
validity assessments by providing greater understanding of the population
upon whom the results are actually based.
However, even if the characteristics are reported, the resulting
information is limited. Regardless of any seeming similarity between
groups, an imbalance could still occur because potentially key
characteristics may not be measured and/or reported or even be measurable.
Therefore, in most instances, the attrition rate, regardless of its
distribution, is important to consider when identifying potential threats
to validity.
Corresponding author: sstrite@delfini.org
1. Sedgwick P. Statistical Question: Sources of bias in randomised
controlled trials II. BMJ 2010; 341:c7053
2. James J, Thomas P, Kerr D. Preventing childhood obesity: two year
follow-up results from the Christchurch obesity prevention programme in
schools (CHOPPS). BMJ2007;335:762-5.
Competing interests: No competing interests