[R-meta] Funnel Plot

Michael Dewey ||@t@ @end|ng |rom dewey@myzen@co@uk
Wed Feb 27 14:42:03 CET 2019

Dear Martin

In addition to Guido's advice you might consider simulating funnel plots 
without asymmetry and then seeing if your looks different against that 
background, preferably by showing them to someone else. Fortunately you 
do not have to write this your self as the good authors of the metaviz 
package (on CRAN) have done it for you and written a helpful vignette.


On 27/02/2019 12:23, Guido Schwarzer wrote:
> Am 27.02.19 um 13:10 schrieb Martin Bauer:
>> Hi there,
>> I am not quite sure, if this funnel plot is symmetrical and if there
>> are any bias. [...]
> I would suggest that you have a look at Sterne et al. (2011).
> According to the recommendations, you could conduct a linear regression
> test for funnel plot asymmetry, e.g., using regtest() in R package
> *metafor* or metabias() in *meta*.
> Best wishes, Guido
> Reference: Sterne JAC, Sutton AJ, Ioannidis JPA, Terrin N, Jones DR, Lau
> J, et al. Recommendations for examining and interpreting funnel plot
> asymmetry in meta-analyses of randomised controlled trials. BMJ.
> 2011;343(jul22 1):d4002.


More information about the R-sig-meta-analysis mailing list