Analysis of heterogeneity (ANOHE)

Share:

Description

(EXPERIMENTAL) Generate an analysis of heterogeneity for the given network. Three types of model are estimated: unrelated study effects, unrelated mean effects, and consistency. Output of the summary function can passed to plot for a visual representation.

Usage

1
mtc.anohe(network, ...)

Arguments

network

An object of S3 class mtc.network.

...

Arguments to be passed to mtc.run or mtc.model. This can be used to set the likelihood/link or the number of iterations, for example.

Details

Analysis of heterogeneity is intended to be a unified set of statistics and a visual display that allows the simultaneous assessment of both heterogeneity and inconsistency in network meta-analysis [van Valkenhoef et al. 2014b (draft)].

mtc.anohe returns the MCMC results for all three types of model. To get appropriate summary statistics, call summary() on the results object. The summary can be plotted.

To control parameters of the MCMC estimation, see mtc.run. To specify the likelihood/link or to control other model parameters, see mtc.model. The ... arguments are first matched against mtc.run, and those that do not match are passed to mtc.model.

Value

For mtc.anohe: an object of class mtc.anohe. This is a list with the following elements:

result.use

The result for the USE model (see mtc.run).

result.ume

The result for the UME model (see mtc.run).

result.cons

The result for the consistency model (see mtc.run).

For summary: an object of class mtc.anohe.summary. This is a list with the following elements:

cons.model

Generated consistency model.

studyEffects

Study-level effect summaries (multi-arm trials downweighted).

pairEffects

Pair-wise pooled effect summaries (from the UME model).

consEffects

Consistency effect summaries.

indEffects

Indirect effect summaries (back-calculated).

isquared.comp

Per-comparison I-squared statistics.

isquared.glob

Global I-squared statistics.

Note

This method should not be considered stable. It is an experimental feature and heavily work in progress. The interface may change at any time.

Author(s)

Gert van Valkenhoef, Joël Kuiper

See Also

mtc.model mtc.run

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.