The case of the misleading funnel plotBMJ 2006; 333 doi: https://doi.org/10.1136/bmj.333.7568.597 (Published 14 September 2006) Cite this as: BMJ 2006;333:597
All rapid responses
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.
We feel honoured that Lau and coauthors selected our systematic
review of inhaled sodium cromoglycate (1) to illustrate the potential
pitfalls of the funnel plot in the context of publication bias. The
authors seem to suggest that the finding of heterogeneity should have
prevented us from publishing a funnel plot. We do not see why a funnel
plot should not be made, as it is a helpful tool for visual inspection,
with or without statistical heterogeneity.
Furthermore, they suggest that by subdividing our funnel plot (figure
2 in their paper) by age of the patients or by study design, the asymmetry
disappears. We disagree. The subdivided funnel plots illustrate that the
asymmetry is especially present in studies with older children and in
cross-over studies. It should be noted that there is a large overlap
between these two characteristics, as well as with publication period
(early studies were done in older children and often had a cross-over
design). In our paper we explored and discussed the possibility put
forward by Lau et al of age of study subjects or design (cross-over or
parallel) being an explanation for the dichotomy of studies, but concluded
prudently (from the result of meta-regression) that “publication period”
was probably the variable explaining it (1). As we pointed out in our
discussion, in the phase a new drug is marketed, omission of small,
negative studies is not unlikely. In a more recent Cochrane review (2), we
suggested to perform a randomized trial in older children, adequately
powered to test the hypothesis that the effect size in this age group was
overestimated by previously published trials.
1. Tasche MJ, Uijen JH, Bernsen RM, de Jongste JC, van der Wouden
JC.Inhaled disodium cromoglycate (DSCG) as maintenance therapy in children
with asthma: a systematic review. Thorax 2000;55:913-20.
2. van der Wouden JC, Tasche MJ, Bernsen RM, Uijen JH, de Jongste JC,
Ducharme FM. Inhaled sodium cromoglycate for asthma in children. Cochrane
Database Syst Rev 2003;(3):CD002173.
Competing interests: No competing interests