[R-meta] Publication Bias

[Gerta Ruecker]

Dear Delphine,

beyond the R code the question is: What does a funnel plot test mean for 
a meta-analysis of proportions? For meta-analyses of comparative effect 
sizes (i.e.,  comparing two interventions), the assumption behind the 
funnel plot tests is that imprecise studies with undesired effects 
(e.g., placebo better than treatment) were suppressed, leading to a gap 
in the funnel plot on the "bad" side. But what is the corresponding 
hypothesis for proportions, for example prevalences? Does the 
funnelplot/the test make sense? How would you interpret ther result?

Best,

Gerta

Am 19.12.2018 um 15:29 schrieb Viechtbauer, Wolfgang (SP):
> Dear Delphine,
>
> For this outcome, the 'Peters test' would in essence be:
>
> library(metafor)
>
> dat <- escalc(measure="PFT", xi=xi, ni=ni, data=dat.debruin2009)
> dat
>
> regtest(dat$yi, dat$vi, model="lm", predictor="ninv")
>
> So, using the inverse sample size as predictor and using 'weighted regression with multiplicative dispersion' as the model.
>
> Best,
> Wolfgang
>
> -----Original Message-----
> From: R-sig-meta-analysis [mailto:r-sig-meta-analysis-bounces using r-project.org] On Behalf Of Nzelle Kayem
> Sent: Wednesday, 19 December, 2018 13:32
> To: r-sig-meta-analysis using r-project.org
> Subject: [R-meta] Publication Bias
>
> Hello,
>
> I found a blog on publication bias and unfortunately my questions were not answered so I thought I will write to you.
>
> I am conducting a review on Ebola in pregnancy and I have completed the proportional meta-analysis.
>
> I got into trouble though when I tried to do the publication bias tests. I used the double arcsine transformation and I have plotted the funnels using the sample size but I don't know the code to use for the peters test. I have used as a guide so far Wang et al 2018 and Viechtbauer W 2010.
>
> Below is an example of the plot
>
> Thanks
>
> Delphine
>
> _______________________________________________
> R-sig-meta-analysis mailing list
> R-sig-meta-analysis using r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis

-- 

Dr. rer. nat. Gerta Rücker, Dipl.-Math.

Institute of Medical Biometry and Statistics,
Faculty of Medicine and Medical Center - University of Freiburg

Stefan-Meier-Str. 26, D-79104 Freiburg, Germany

Phone:    +49/761/203-6673
Fax:      +49/761/203-6680
Mail:     ruecker using imbi.uni-freiburg.de
Homepage: https://www.imbi.uni-freiburg.de/persons/ruecker/person_view