Learn R Programming

netmeta (version 3.7-0)

rankogram.netmeta: Calculate rankogram

Description

This function calculates the probabilities of each treatment being at each possible rank and the SUCRAs (Surface Under the Cumulative RAnking curve) in frequentist network meta-analysis.

Usage

# S3 method for netmeta
rankogram(
  x,
  nsim = gs("nsim"),
  common = x$common,
  random = x$random,
  small.values = x$small.values,
  cumulative.rankprob = FALSE,
  keep.samples = FALSE,
  nchar.trts = x$nchar.trts,
  warn.deprecated = gs("warn.deprecated"),
  ...
)

Value

An object of class rankogram with corresponding print

and plot function. The object is a list containing the following components:

x, nsim

As defined above.

common, random

As defined above.

small.values

As defined above.

cumulative.rankprob

As defined above.

nchar.trts

As defined above.

call

Function call.

version

Version of R package netmeta used to create object.

The following components are available if argument common = TRUE:

ranking.common

SUCRA values for the common effects model.

ranking.matrix.common

Numeric matrix giving the probability of each treatment being at each possible rank for the common effects model.

cumrank.matrix.common

Numeric matrix giving the cumulative ranking probabilities for the common effects model.

meanranks.common

Mean ranks for the common effects model.

medianranks.common

Median ranks for the common effects model.

samples.common

Generated samples for the common effects model (if keep.samples = TRUE).

The following components are available if argument random = TRUE:

ranking.random

SUCRA values for the random effects model.

ranking.matrix.random

Numeric matrix giving the probability of each treatment being at each possible rank for the random effects model.

cumrank.matrix.random

Numeric matrix giving the cumulative ranking probabilities for the random effects model.

meanranks.random

Mean ranks for the random effects model.

medianranks.random

Median ranks for the random effects model.

samples.random

Generated samples for the random effects model (if keep.samples = TRUE).

Arguments

x

An object of class netmeta.

nsim

Number of repetitions.

common

A logical indicating to compute ranking probabilities and SUCRAs for the common effects model.

random

A logical indicating to compute ranking probabilities and SUCRAs for the random effects model.

small.values

A character string specifying whether small treatment effects indicate a beneficial ("desirable") or harmful ("undesirable") effect, can be abbreviated.

cumulative.rankprob

A logical indicating whether cumulative ranking probabilities should be printed.

keep.samples

A logical indicating whether to keep the generated samples.

nchar.trts

A numeric defining the minimum number of characters used to create unique treatment names.

warn.deprecated

A logical indicating whether warnings should be printed if deprecated arguments are used.

...

Additional arguments (ignored).

Author

Theodoros Papakonstantinou [email protected], Guido Schwarzer [email protected]

Details

We derive a matrix showing the probability of each treatment being at each possible rank. To this aim, we use resampling from a multivariate normal distribution with estimated network effects as means and corresponding estimated variance covariance matrix. We then summarise them using the ranking metric SUCRAs (Surface Under the Cumulative RAnking curve).

References

Salanti G, Ades AE, Ioannidis JP (2011): Graphical methods and numerical summaries for presenting results from multiple-treatment meta-analysis: an overview and tutorial. Journal of Clinical Epidemiology, 64, 163--71

See Also

netmeta, netrank, plot.rankogram, Woods2010

Examples

Run this code
pw <- pairwise(treatment, event = r, n = N, studlab = author,
  data = Woods2010, sm = "OR")
nma <- netmeta(pw, small.values = "desirable")

set.seed(1909) # get reproducible results
rnk <- rankogram(nma, nsim = 100)
rnk
print(rnk, cumulative.rankprob = TRUE)

# Also print mean ranks
summary(rnk)

plot(rnk)

Run the code above in your browser using DataLab