# Install release version from CRAN
install.packages("chmsflow")
# Install the most recent version from GitHub
devtools::install_github("Big-Life-Lab/chmsflow")1. Load packages
2. Transform variables into harmonized versions
Use rec_with_table() of recodeflow to transform the variables of a CHMS dataset. Cycle data object always has to be called “cyclex” in order for recoding to work properly.
At the RDC, each cycle is split into multiple components (e.g., household data, clinic data, laboratory data, etc.), so it is the analyst’s responsibility to merge their required components in one database named “cyclex”. However, keep medication data separate from the rest of the cycle data (see here).
# Load recodeflow
library(recodeflow)
# Recoding basic variables
cycle4_ages <- rec_with_table(cycle4, "clc_age", variable_details = variable_details, log = TRUE)
head(cycle4_ages)
cycle4_sexes <- rec_with_table(cycle4, "clc_sex", variable_details = variable_details, log = TRUE)
head(cycle4_sexes)
# Recoding a transformed variable (cont to cat)
cycle4_categorical_ages <- rec_with_table(cycle4, "agegroup4", variable_details = variable_details, log = TRUE)
head(cycle4_categorical_ages)
# Recoding a derived variable
cycle4_adjusted_SBPs <- rec_with_table(cycle4, c("bpmdpbps", "sbp_adj"), variable_details = variable_details, log = TRUE)
head(cycle4_adjusted_SBPs)