Talk:Funnel plot

Latest comment: 5 years ago by 192.42.144.8 in topic Real plot

Real plot

edit

It'd be nifty to have a real funnel plot. The current example isn't necessarily intuitive and obviously is just a mockup.

May I suggest http://www.genomesunzipped.org/wp-content/uploads/2011/11/NatGen_funnel-plot_cropped.gif ? http://marginalrevolution.com/marginalrevolution/2011/11/small-samples-mean-statistically-significant-results-should-usually-be-ignored.html says it's "adapted from Ioannidis 2001 et al., Nat Genet 29:306-309". --Gwern (contribs) 17:42 30 November 2011 (GMT)

The caption under the current funnel plot needs to be changed. It currently says the following: "An example funnel plot showing no publication bias." That statement is misleading at best and propagates misunderstandings about what asymmetry can be interpreted as. Cf. for example 'Funnel plot asymmetry should not be equated with publication bias, because it has a number of other possible causes. ' at https://www.bmj.com/content/343/bmj.d4002 — Preceding unsigned comment added by 192.42.144.8 (talk) 20:43, 24 March 2019 (UTC)Reply

Types of funnel plot

edit

Looking up this topic, I was expecting to find the 'bugle' type of funnel plot shown in Figure 2 of http://medicine.cf.ac.uk/media/filer_public/2010/09/24/spiegelhalter_stats_in_med_funnel_plots.pdf - this plot is designed to indicate to the viewer the difference in precision of a set of samples due to differing sample sizes, to enable better identification of outliers where a ranking, even with confidence intervals displayed might be more open to misinterpretation. Should that kind of plot be included here, or does it belong elsewhere? Neilplatform1 (talk) 18:46, 1 December 2011 (UTC)Reply

The type of funnel plot to which you refer should not be included here. I think it would be best if there was a disambiguation page since these two types of funnel plot are not used to represent the same sort of data, nor are they visually similar.Ts4079 (talk) 12:42, 9 October 2014 (UTC)Reply

Too negative regarding funnel plots

edit

Funnel plots are an excellent first-pass implementation of meta-analysis, exactly where the beginning meta-analyst should start. The current article focuses too much on the shortcomings of funnel plots (the citations are largely about failures of funnel plots). I recommend -- and will implement when I have spare time -- publications by T.D. Stanley on meta-analysis, e.g., https://books.google.fr/books?id=jSQEdEsL7VoC Michaelaoash (talk) 16:15, 3 June 2015 (UTC)Reply

Quotation section

edit

Why is there a section called Quotation? Should this be renamed? Njspix (talk) 19:45, 22 March 2018 (UTC)Reply