mtc.network: Create an mtc.network

Description

Creates an object of class mtc.network

Usage

mtc.network(data.ab=data, treatments=NULL, description="Network",
            data.re=NULL, studies=NULL, data=NULL)
# S3 method for mtc.network
plot(x, layout=igraph::layout.circle, dynamic.edge.width=TRUE, use.description=FALSE, ...)

Arguments

data.ab

Arm-level data. A data frame defining the arms of each study, containing the columns `study' and `treatment', where `treatment' must refer to an existing treatment ID if treatments were specified. Further columns define the data per arm, and depend on the likelihood/link to be used. See mtc.model for supported likelihood/links and their data requirements.

data.re

Relative effect data. A data frame defining the arms of each study, containing the columns `study' and `treatment', where `treatment' must refer to an existing treatment ID if treatments were specified. The column `diff' specifies the mean difference between the current arm and the baseline arm; set `diff=NA' for the baseline arm. The column `std.err' specifies the standard error of the mean difference (for non-baseline arms). For trials with more than two arms, specify the standard error of the mean of the baseline arm in `std.err', as this determines the covariance of the differences.

treatments

Optional. A data frame with columns `id' and `description' defining the treatments or a vector giving the treatment IDs.

studies

Optional. A data frame with a `study' column naming the studies and additional columns containing covariate values.

description

Optional. Short description of the network.

data

Deprecated. Arm-level data; automatically assigned to data.ab if it is not specified. Present for compatibility with older versions.

An mtc.network object.

layout

An igraph-compatible layout.

dynamic.edge.width

If set to TRUE, dynamically set the edge width based on the number of studies.

use.description

Display treatment descriptions instead of treatment IDs.

...

Additional arguments passed to plot.igraph.

Value

For mtc.network, an object of the class mtc.network which is a list containing:

description

A short description of the network

treatments

A data frame describing the treatments

data.ab

A data frame containing the network data (arm-level)

data.re

A data frame containing the network data (relative effects)

studies

A data frame containing study-level information (covariates)

These are cleaned up and standardized versions of the arguments provided, or generated defaults for `treatments' if the argument was omitted.

Details

One-arm trials are automatically removed, which results in a warning.

Also see mtc.data.studyrow for a convenient way to import data from the one-study-per-row format, which is very popular for BUGS code.

Examples

Run this code

# NOT RUN {
# Create a new network by specifying all information.
treatments <- read.table(textConnection('
  id  description
  A   "Treatment A"
  B   "Treatment B"
  C   "Treatment C"'), header=TRUE)
data <- read.table(textConnection('
  study  treatment  responders  sampleSize
  01     A          2           100
  01     B          5           100
  02     B          6           110
  02     C          1           110
  03     A          3           60
  03     C          4           80
  03     B          7           80'), header=TRUE)
network <- mtc.network(data, description="Example", treatments=treatments)
plot(network)

# Create a new network by specifying only the data.
data <- read.table(textConnection('
  study  treatment  mean   std.dev  sampleSize
  01     A          -1.12  0.6      15
  01     B          -1.55  0.5      16
  02     A          -0.8   0.7      33
  02     B          -1.1   0.5      31'), header=TRUE)
network <- mtc.network(data)

# Print the network
print(network)
## MTC dataset: Network
##   study treatment  mean std.dev sampleSize
## 1     1         A -1.12     0.6         15
## 2     1         B -1.55     0.5         16
## 3     2         A -0.80     0.7         33
## 4     2         B -1.10     0.5         31
# }