netconnection.default: Get information on network connectivity (number of subnetworks, distance matrix)

Description

To determine the network structure and to test whether a given network is fully connected. Network information is provided as a triple of vectors treat1, treat2, and studlab where each row corresponds to an existing pairwise treatment comparison (treat1, treat2) in a study (studlab). The function calculates the number of subnetworks (connectivity components; value of 1 corresponds to a fully connected network) and the distance matrix (in block-diagonal form in the case of subnetworks). If some treatments are combinations of other treatments or have common components, an analysis based on the additive network meta-analysis model might be possible, see discomb function.

Usage

# S3 method for default
netconnection(
  data = NULL,
  treat1,
  treat2,
  studlab = NULL,
  subset = NULL,
  sep.trts = ":",
  nchar.trts = 666,
  title = "",
  details.disconnected = FALSE,
  warn = FALSE,
  ...
)
# S3 method for pairwise
netconnection(
  data,
  treat1,
  treat2,
  studlab = NULL,
  subset = NULL,
  sep.trts = ":",
  drop.NA = TRUE,
  nchar.trts = 666,
  title = "",
  details.disconnected = FALSE,
  warn = FALSE,
  ...
)
# S3 method for netmeta
netconnection(
  data,
  sep.trts = data$sep.trts,
  nchar.trts = data$nchar.trts,
  title = data$title,
  details.disconnected = FALSE,
  warn = FALSE,
  ...
)
# S3 method for netcomb
netconnection(
  data,
  sep.trts = data$sep.trts,
  nchar.trts,
  title = data$title,
  details.disconnected = FALSE,
  warn = FALSE,
  ...
)
# S3 method for netconnection
print(
  x,
  digits = max(4, .Options$digits - 3),
  nchar.trts = x$nchar.trts,
  details = FALSE,
  details.disconnected = x$details.disconnected,
  ...
)
netconnection(data, ...)

Value

An object of class netconnection with corresponding print function. The object is a list containing the following components:

treat1, treat2, studlab, title, warn, nchar.trts: As defined above.
k: Total number of studies.
m: Total number of pairwise comparisons.
n: Total number of treatments.
n.subnets: Number of subnetworks; equal to 1 for a fully connected network.
D.matrix: Distance matrix.
A.matrix: Adjacency matrix.
L.matrix: Laplace matrix.
call: Function call.
version: Version of R package netmeta used to create object.

Arguments

data: A data frame, e.g., created with pairwise.
treat1: Label / number for first treatment (ignored if data was created with pairwise).
treat2: Label / number for second treatment (ignored if data was created with pairwise).
studlab: Study labels (ignored if data was created with pairwise).
subset: An optional vector specifying a subset of studies to be used.
sep.trts: A character used in comparison names as separator between treatment labels.
nchar.trts: A numeric defining the minimum number of characters used to create unique treatment names.
title: Title of meta-analysis / systematic review.
details.disconnected: A logical indicating whether to print more details for disconnected networks.
warn: A logical indicating whether warnings should be printed.
...: Additional arguments (ignored at the moment)
drop.NA: A logical indicating whether comparisons with missing treatment estimates or standard errors should be considered.
x: An object of class netconnection.
digits: Minimal number of significant digits, see print.default.
details: A logical indicating whether to print the distance matrix.

Author

Gerta Rücker gerta.ruecker@uniklinik-freiburg.de, Guido Schwarzer guido.schwarzer@uniklinik-freiburg.de

Examples

Run this code

# \donttest{
# Transform data from long arm-based to contrast-based format
#
pw <- pairwise(studlab = study, treat = treatment,
  n = n, mean = mean, sd = sd, data = Senn2013,
  varnames = c("MD", "seMD"))

nc1 <- netconnection(pw)
nc1

# Extract number of (sub)networks
#
nc1$n.subnets

# Extract distance matrix
#
nc1$D.matrix

# Artificial example with two subnetworks
#
t1 <- c("G", "B", "B", "D", "A", "F")
t2 <- c("B", "C", "E", "E", "H", "A")
#
nc2 <- netconnection(t1, t2)
print(nc2, details = TRUE)

# Number of subnetworks
#
nc2$n.subnets

# Extract distance matrix
#
nc2$D.matrix

# Conduct network meta-analysis (results in an error message due to
# unconnected network)
try(nma <- netmeta(1:6, 1:6, t1, t2, 1:6))

# Conduct network meta-analysis on first subnetwork
#
nma.1 <- netmeta(1:6, 1:6, t1, t2, 1:6, subset = nc2$subnet == 1)

# Conduct network meta-analysis on second subnetwork
#
nma.2 <- netmeta(1:6, 1:6, t1, t2, 1:6, subset = nc2$subnet == 2)

nma.1
nma.2
# }