bucher: Simple indirect (Bucher) meta-analysis

In RichardBirnie/mautils: Utilities to facilitate an automated workflow for meta-analysis

Description

Simple indirect (Bucher) meta-analysis

Usage

bucher(abTE, se.abTE, cbTE, se.cbTE, effect, model, continuous, intervention,
  comparator, common, backtransf = FALSE, ab.studies, cb.studies)

Arguments

abTE	Numeric. The treatment effect for a vs b. e.g. log OR, log HR, mean difference
se.abTE	Numeric. The standard error of the treatment effect for a vs b, e.g. se of log OR
cbTE	Numeric. The treatment effect for c vs b. e.g. log OR, log HR, mean difference
se.cbTE	Numeric. The standard error of the treatment effect for c vs b, e.g. se of log OR
effect	Character string describing the effect measure, e.g. 'Rate Ratio' or 'log Odds Ratio'
model	Character string indicating whether abTE and cbTE come from a fixed effect model or a random effect model
continuous	Logical (TRUE/FALSE) indicating whether the effect measure is continuous (mean difference) or a ratio measure (odds ratio, hazard ratio etc).
intervention	Character string. Name of the intervention treatment
comparator	Character string. Name of the comparator treatment
common	Character string. Name of the common comparator that links the indirect comparison, e.g. placebo
backtransf	Logical indicating whether the results should be exponentiated or not. If abTE and cbTE are on the log scale (e.g. log hazard ratio) set this to TRUE to return the exponentiated results (e.g. hazard ratio). If TRUE this will return both the log estimates and the exponentiated estimates
ab.studies	Character string giving the names of studies in the A vs B comparison separated by commas
cb.studies	Character string giving the names of studies in the C vs B comparison separated by commas

Details

Calculate an indirect estimate of the relative effect of two treatments using the Bucher method

The inputs are the relative treatment effects for two pairs of treatments linked by a common comparator. For example, if you have the relative effects (e.g. log hazard ratio) for treatment A vs placebo and treatment C vs placebo then this function will return the relative effect of treatment A compared to treatment C.

This function is mainly intended to be called from doBucher but can be used directly if required.

effect, model, intervention, comparator and common are used for labels only. The results depend only on abTE, cbTE and the respective standard errors.

@return A data frame with the following columns:

• Intervention The name of the intervention

• Comparator The name of the comparator

• Common The name of the common treatment linking intervention and comparator

• Effect The type of effect measure. Takes the value of the effect argument

• Model The type of model. Should be 'Fixed', 'Random' or NA

• log.TE.ind The treatment effect on log scale, e.g. log OR

• log.lower.ind, log.upper.ind The upper and lower 95% confidence intervals for the log treatment effect

• se.log.TE.ind The standard error for the log treatment effect

• TE.ind, lower.ind, upper.ind The treatment effect with lower and upper confidence intervals backtransformed to a linear scale

• n.studies The number of studies included in the analysis

• Studies The names of the studies included in the analysis

See Also

doBucher

RichardBirnie/mautils documentation built on July 12, 2019, 8:56 p.m.