Repository files navigation

metagroup provides a suite of tools to uncover hidden structures in meta-analytic data. It uses a two-step process to perform meaningful subgroup analysis:

1. Group: Use iterative grouping functions (e.g.,mgbin(),mgcont()) to partition studies into statistically homogeneous clusters based on their effect size data.
2. Interpret: Use themeaning() function and its associatedplot() method to analyze these new subgroups and understand their composition based on study-level characteristics (e.g., country, setting).

This approach helps to provide a deeper, more data-driven interpretation of heterogeneity in a meta-analysis.

Install the stable version ofmetagroup from CRAN with:

install.packages("metagroup")

Install the development version ofmetagroup from GitHub with:

# install.packages("remotes")remotes::install_github("asmpro7/metagroup")

Here is a basic example of the core workflow: first grouping the studies, then finding the meaning behind the groups.

# 1. Load the packagelibrary(metagroup)# 2. Step 1: Group the studies by homogeneity# The result contains the original data with a new 'subgroup' columngrouped_results<- mgbin(data=study_data,event.e=event.e,n.e=n.e,event.c=event.c,n.c=n.c,studlab=studlab,sm="OR")# 3. Step 2: Analyze the composition of the new subgroupsmeaning_results<- meaning(data=grouped_results,variables= c("country","setting"))# Print the summary table to see the dominant characteristics of each groupprint(meaning_results)# Plot the results to visualize the composition of all groupsplot(meaning_results)