plots:contour_enhanced_funnel_plot_2

**This is an old revision of the document!**

Here is another example of a contour-enhanced funnel plot (Peters et al., 2008) (see here for a brief discussion of the idea behind such plots). This one is a very close re-creation of Figure 2(b) from Peters et al. (2008). Note that the values for `ylim`

technically have to be greater than 0 when using the inverse standard error on the y-axis, but we can get essentially the same limits by using a very small value for the lower limit. Also, the dataset used by Peters et al. (2008) contains an extra study, which isn't included in the Cochrane review by Graves et al. (2010).

library(metafor) ### decrease margins so the full space is used par(mar=c(5,4,1,2)) ### calculate log odds ratios and corresponding sampling variances dat <- escalc(measure="OR", ai=ai, n1i=n1i, ci=ci, n2i=n2i, data=dat.graves2010) ### create contour enhanced funnel plot funnel(dat$yi, dat$vi, yaxis="seinv", xlim=c(-3,2), ylim=c(.00001,8), xaxs="i", yaxs="i", las=1, level=c(.10, .05, .01), shade=c("white", "gray55", "gray75"), legend=TRUE, back="gray90", ylab="Precision (1/se)", lty=0)

Graves, P. M., Deeks, J. J., Demicheli, V., & Jefferson, T. (2010). Vaccines for preventing cholera: Killed whole cell or other subunit vaccines (injected). *Cochrane Database of Systematic Reviews, 8*, CD000974.

Peters, J. L., Sutton, A. J., Jones, D. R., Abrams, K. R., & Rushton, L. (2008). Contour-enhanced meta-analysis funnel plots help distinguish publication bias from other causes of asymmetry. *Journal of Clinical Epidemiology, 61*(10), 991–996.

plots/contour_enhanced_funnel_plot_2.1584892251.txt.gz · Last modified: 2020/03/22 15:50 by Wolfgang Viechtbauer

Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Noncommercial-Share Alike 4.0 International