league.crossnma {crossnma}  R Documentation 
Produces a league table that contains point estimates of relative effects for all possible pairs of treatments along with 95% credible intervals obtained with the quantile method.
## S3 method for class 'crossnma'
league(
x,
median = TRUE,
exp = FALSE,
order = NULL,
cov1.value = NULL,
cov2.value = NULL,
cov3.value = NULL,
digits = 2,
direction = "wide",
...
)
league(x, ...)
## S3 method for class 'league.crossnma'
print(x, ...)
x 
An object created with 
median 
A logical indicating whether to use the median (default) or mean to measure relative treatment effects. 
exp 
If TRUE (default), odds ratios are displayed. If FALSE, log odds ratios will be presented. 
order 
A vector of treatment names (character) representing the order in which to display these treatments. 
cov1.value 
The participant covariate value of

cov2.value 
The participant covariate value of

cov3.value 
The participant covariate value of

digits 
The number of digits to be used when displaying the results. 
direction 
The format to display the league table. Two options "wide" (default) and "long". 
... 
Additional arguments (ignored at the moment). 
A league table. Row names indicate comparator treatments. The table will be displayed in a long or wide formatting.
Tasnim Hamza tasnim.hamza@ispm.unibe.ch
# We conduct a network metaanalysis assuming a randomeffects
# model.
# The data comes from randomizedcontrolled trials and
# nonrandomized studies (combined naively)
head(ipddata) # participantlevel data
head(stddata) # studylevel data
# Create a JAGS model
mod < crossnma.model(treat, id, relapse, n, design,
prt.data = ipddata, std.data = stddata,
reference = "A", trt.effect = "random", method.bias = "naive")
# Fit JAGS model
# (suppress warning 'Adaptation incomplete' due to n.adapt = 20)
fit <
suppressWarnings(crossnma(mod, n.adapt = 20,
n.iter = 50, thin = 1, n.chains = 3))
# Create league tables
league(fit, exp = TRUE) # wide format
league(fit, exp = TRUE, direction = "long") # long format