binmeta.fi: Calculate a fragility index for a meta analysis with binary...

In brb225/FragilityTools: Toolbox For Patient Count Fragility Measures

Description

This is a function which is a wrapper around internal functions which calculate the fragility index for different data types and test specifications. It is used for meta analyses on binary data. This function makes use of p-value calculators from the meta R package.

Usage

binmeta.fi(
  data,
  restr.study = NULL,
  method = "MH",
  sm = "RR",
  cl = NULL,
  alpha = 0.05,
  verbose = FALSE,
  q = 0
)

Arguments

data	a dataframe with the number of events and observations for the control and treatment groups as columns. The names of the studies must be the rownames, and the names cannot contain two consuctive dots. The order should be event.e, n.e, event.c, n.c, as in meta::binmeta
restr.study	a character vector giving the names of the studies whose patients are allowed to have response changes. The default is all the studies.
method	A character string indicating which method is to be used for pooling of studies. One of "Inverse", "MH", "Peto", "GLMM", or "SSW", can be abbreviated. (From meta.')
sm	A character string indicating which summary measure ("RR", "OR", "RD", or "ASD"). See the 'meta“ package documention for more details.
cl	a cluster from the parallel package, used to compute fragility index over each modified observation at each stage of the greedy algorithm
alpha	a number for the size of test
verbose	a logical value for whether to print status updates while running
q	the sufficiently likely threshold, defaults to 0, permitting all modifications. Any empirical conditional outcome probability strictly lower than q will not be permitted to receive outcome modifications.

Value

the output of greedy.fi specialized to the meta analysis case

Examples

data(Olkin95, package = "meta")
out <- binmeta.fi(data = Olkin95[1:5, -2], restr.study = c("Dewar", "Lippschutz"))
out$FI

brb225/FragilityTools documentation built on Jan. 21, 2022, 1:26 a.m.