metacor.DSL {metacor} | R Documentation |
Implements the DerSimonian-Laird (DSL) random-effect meta-analytical approach with correlation coefficients as effect sizes, as described by Schulze (2004).
metacor.DSL(r, n, labels, alpha = 0.05, plot = TRUE, xlim = c(-1, 1), transform = TRUE)
r |
vector of correlations |
n |
vector of sample sizes |
labels |
vector of the study names |
alpha |
alpha-level for the main test and for the confidence intervals |
plot |
logical; should a forest plot be returned? |
xlim |
range of the x-axis of the forest plot |
transform |
logical; should the z-values be back-transformed to r-space? |
z |
vector of the z-values |
z.var |
vector of the variances of each z |
z.lower |
the lower limits of the confidence intervals for each z |
z.upper |
the upper limits of the confidence intervals for each z |
z.mean |
the mean effect size z |
r.mean |
the mean effect size r, back-transformed from z-space |
z.se |
the standard error of z.mean |
z.mean.lower |
the lower limit of the confidence interval for z.mean |
r.mean.lower |
the lower limit of the confidence interval for r.mean, back-transformed from z-space |
z.mean.upper |
the upper limit of the confidence interval for z.mean |
r.mean.upper |
the upper limit of the confidence interval for r.mean, back-transformed from z-space |
p |
the p-value for the null hypothesis H0 -> z.mean = 0 |
Etienne Laliberte etiennelaliberte@gmail.com http://www.elaliberte.info/
Schulze, R. (2004) Meta-analysis: a comparison of approaches. Hogrefe & Huber, Gottingen, Germany.
data(lui) lui <- lui[order(lui$r.FDis),] test <- metacor.DSL(lui$r.FDis, lui$n, lui$label) test