PublicationBias
is an R package that provides bias
correction and sensitivity analysis for publication bias in
meta-analyses (per Mathur &
VanderWeele, 2020).
You can install PublicationBias from CRAN with:
install.packages("PublicationBias")
You can install the development version of PublicationBias from GitHub with:
# install.packages("devtools")
::install_github("mathurlabstanford/PublicationBias") devtools
Start by generating some example data from the metafor
package.
library(PublicationBias)
<- metafor::escalc(measure = "RR", ai = tpos, bi = tneg, ci = cpos,
dat di = cneg, data = dat.bcg)
Calculate the meta-analytic effect size estimate, correcting for an assumed selection ratio of 5 (i.e., affirmative results are 5x more likely to be published than nonaffirmative ones).
pubbias_meta(yi = dat$yi, vi = dat$vi, selection_ratio = 5,
model_type = "fixed", favor_positive = FALSE)
Calculate how high the selection ratio would need to be to attenuate the effect size estimate to the null.
pubbias_svalue(yi = dat$yi, vi = dat$vi, q = 0,
model_type = "fixed", favor_positive = FALSE)