process_agd: Pre-process aggregate data

In maicplus: Matching Adjusted Indirect Comparison

Pre-process aggregate data

Description

This function checks the format of the aggregate data. Data is required to have three columns: STUDY, ARM, and N. Column names that do not have legal suffixes (MEAN, MEDIAN, SD, COUNT, or PROP) are dropped. If a variable is a count variable, it is converted to proportions by dividing the sample size (N). Note, when the count is specified, proportion is always calculated based on the count, that is, specified proportion will be ignored if applicable. If the aggregated data comes from multiple sources (i.e. different analysis population) and sample size differs for each variable, one option is to specify proportion directly instead of count by using suffix _PROP.

Usage

process_agd(raw_agd)

Arguments

raw_agd

raw aggregate data should contain STUDY, ARM, and N. Variable names should be followed by legal suffixes (i.e. MEAN, MEDIAN, SD, COUNT, or PROP).

Value

pre-processed aggregate level data

Examples

data(agd)
agd <- process_agd(agd)

maicplus documentation built on April 4, 2025, 2:17 a.m.