Function to carry out the rank correlation test for funnel plot asymmetry.
ranktest(x, vi, sei, subset, data, digits, ...)
a vector with the observed effect sizes or outcomes or an object of class
vector with the corresponding sampling variances (ignored if
x is an object of class
vector with the corresponding standard errors (note: only one of the two,
sei, needs to be specified).
optional (logical or numeric) vector to specify the subset of studies that should be included in the test (ignored if
x is an object of class
optional data frame containing the variables given to the arguments above.
optional integer to specify the number of decimal places to which the printed results should be rounded.
The function carries out the rank correlation test as described by Begg and Mazumdar (1994). The test can be used to examine whether the observed effect sizes or outcomes and the corresponding sampling variances are correlated. A high correlation would indicate that the funnel plot is asymmetric, which may be a result of publication bias.
One can either pass a vector with the observed effect sizes or outcomes (via
x) and the corresponding sampling variances via
vi (or the standard errors via
sei) to the function or an object of class
"rma". When passing a model object, the model must be a model without moderators (i.e., either an equal- or a random-effects model).
An object of class
"ranktest". The object is a list containing the following components:
the estimated value of Kendall's tau rank correlation coefficient.
the corresponding p-value for the test that the true tau value is equal to zero.
The results are formatted and printed with the
The method does not depend on the model fitted. Therefore, regardless of the model passed to the function, the results of the rank test will always be the same. See
regtest for tests of funnel plot asymmetry that are based on regression models and model dependent.
The function makes use of the
cor.test function with
method="kendall". If possible, an exact p-value is provided; otherwise, a large-sample approximation is used.
Begg, C. B., & Mazumdar, M. (1994). Operating characteristics of a rank correlation test for publication bias. Biometrics, 50(4), 1088–1101. https://doi.org/10.2307/2533446
Viechtbauer, W. (2010). Conducting meta-analyses in R with the metafor package. Journal of Statistical Software, 36(3), 1–48. https://doi.org/10.18637/jss.v036.i03
### calculate log risk ratios and corresponding sampling variances dat <- escalc(measure="RR", ai=tpos, bi=tneg, ci=cpos, di=cneg, data=dat.bcg) ### fit random-effects model res <- rma(yi, vi, data=dat) ### carry out the rank correlation test ranktest(res) #> #> Rank Correlation Test for Funnel Plot Asymmetry #> #> Kendall's tau = 0.0256, p = 0.9524 #> ### can also pass the observed outcomes and corresponding sampling variances to the function ranktest(yi, vi, data=dat) #> #> Rank Correlation Test for Funnel Plot Asymmetry #> #> Kendall's tau = 0.0256, p = 0.9524 #>